© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14590
    Prev
    Next
    INDEX
    Explanations

    terms related to processes or mechanisms involved in assembly, adjustment, or installation of physical components

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

    words and phrases related to assembly, installation, and construction processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    __);
    -0.61
    ⓘ
    -0.56
     autorytatywna
    -0.54
    ftagPool
    -0.54
     يتيمه
    -0.52
     plufieurs
    -0.51
    verwijspagina
    -0.50
     disambiguazione
    -0.49
     disponibilités
    -0.49
    Quoi
    -0.47
    POSITIVE LOGITS
     finishing
    0.62
     finish
    0.55
     final
    0.53
     finished
    0.49
     assembling
    0.46
     Finishing
    0.46
     install
    0.46
    finishing
    0.43
     assemble
    0.43
     finishes
    0.42
    Activations Density 0.253%

    No Known Activations