© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2378
    Prev
    Next
    INDEX
    Explanations

    terms related to processes and synchronization in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical and scientific process terms related to measurement, computation, and system dynamics.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    phrases that define or explain concepts in technical or academic writing.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    definitions and expository statements that specify what a term, process, or task “is,” “consists of,” or “refers to,” often outlining purpose or procedure.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    technical or formal descriptions of processes, functions, or operations, often in academic or patent document contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nadel
    -0.42
    #+#
    -0.41
     Bahan
    -0.40
    ViewHolder
    -0.40
    routeProvider
    -0.39
    hadiran
    -0.39
     Brenn
    -0.39
    hamilan
    -0.38
     değ
    -0.38
     holders
    -0.38
    POSITIVE LOGITS
     process
    0.65
     initiation
    0.58
     activity
    0.57
     aktivitet
    0.56
     činnosti
    0.54
     undertaken
    0.52
     operations
    0.52
     processes
    0.51
     operation
    0.51
     done
    0.51
    Activations Density 0.754%

    No Known Activations