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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10889
    Prev
    Next
    INDEX
    Explanations

    declarations of variables or methods with access modifiers, particularly 'private'

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

    "private" keyword in code

    np_acts-logits-general · gemini-2.0-flash

    private member declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MatDialog
    -0.82
     فريبيس
    -0.78
     getItemCount
    -0.76
     pstmt
    -0.76
    TemporalType
    -0.72
     itſelf
    -0.70
     NDEBUG
    -0.70
     Италијани
    -0.70
    AnimationsModule
    -0.69
     EINVAL
    -0.69
    POSITIVE LOGITS
     static
    1.11
     readonly
    0.85
     final
    0.70
     const
    0.67
    Static
    0.61
    static
    0.60
    帖最后由
    0.60
    SourceChecksum
    0.59
    writeString
    0.57
    چه
    0.56
    Activations Density 0.020%

    No Known Activations