© 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. 10153
    Prev
    Next
    INDEX
    Explanations

    financial or quantitative data relevant to health studies

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

    numerical data and statistical information presented in tables or structured formats.

    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
     للاسماء
    -0.48
    +#+#
    -0.43
     ComVisible
    -0.43
    AntiForgeryToken
    -0.42
    AnimationsModule
    -0.41
     برانيه
    -0.37
    __*/
    -0.36
     Apostle
    -0.36
     AssemblyTitle
    -0.36
     matin
    -0.36
    POSITIVE LOGITS
     समीक्षाओं
    0.52
    GTCX
    0.49
    
    0.40
     poleg
    0.38
    VersionUID
    0.38
     translating
    0.38
    RTEX
    0.37
    Besos
    0.36
    illère
    0.36
     indu
    0.36
    Activations Density 0.464%

    No Known Activations