© 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. 9799
    Prev
    Next
    INDEX
    Explanations

    code structure or syntax elements indicating data processing or organization

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

    code with indentation and whitespace formatting patterns.

    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
     MainAxisSize
    -0.88
    ConstraintMaker
    -0.85
    LookAnd
    -0.84
     Waſſer
    -0.84
    niſſe
    -0.84
     Wicidata
    -0.83
     HasFactory
    -0.82
     beſch
    -0.80
     Normdatei
    -0.80
    AndEndTag
    -0.79
    POSITIVE LOGITS
    //
    1.13
    <strong>
    1.12
     —
    1.05
     //
    0.94
    —
    0.93
    <b>
    0.90
     –
    0.83
    /**
    0.76
     --
    0.74
    ---
    0.73
    Activations Density 0.556%

    No Known Activations