© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 7526
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structure in programming code

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

    assignment statements where values are assigned to object properties or variables.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mainwindow
    -0.31
    ChildScrollView
    -0.30
    Референце
    -0.29
     cellpadding
    -0.27
     trajets
    -0.27
    audiovisuel
    -0.27
    endcsname
    -0.27
    Parcelize
    -0.26
    楼主
    -0.26
     ब्रेकडाउन
    -0.25
    POSITIVE LOGITS
    zzleHttp
    0.68
    CloseOperation
    0.64
    FailureListener
    0.63
    sizeCache
    0.62
    ReusableCell
    0.59
    ArgsConstructor
    0.57
    ----</
    0.57
    toprule
    0.57
    ckså
    0.56
    envolvimento
    0.56
    Activations Density 0.213%

    No Known Activations