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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 8817
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with data structures and systems, particularly in the context of programming and technology

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

    technical and scientific terminology, particularly nouns related to systems, devices, research subjects, and formal/specialized contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    domain-specific technical or scientific count nouns—especially names of hardware, network/computing components, data structures, and lab entities, often in plural form.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.47
    EnableWeb
    -0.41
     ligiloj
    -0.37
    PackageInfo
    -0.35
     lượt
    -0.35
     непри
    -0.35
     Austin
    -0.34
    djangoproject
    -0.34
    AutoField
    -0.33
     autonome
    -0.33
    POSITIVE LOGITS
    Hochspringen
    0.59
     CanadaChoose
    0.47
    Vanjske
    0.46
     considerazione
    0.44
     titulado
    0.44
    Rats
    0.44
     MainAxisSize
    0.42
    Conversely
    0.42
    Anybody
    0.41
    Étymologie
    0.41
    Activations Density 2.433%

    No Known Activations