© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 6328
    Prev
    Next
    INDEX
    Explanations

    location-based phrases and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BoxShadow
    -0.61
    WriteBarrier
    -0.53
    tagext
    -0.50
    SSON
    -0.49
    󠁢
    -0.49
    $_['
    -0.48
    Parcelize
    -0.48
    外部リンク
    -0.47
    isContained
    -0.47
     "}
    -0.47
    POSITIVE LOGITS
     Extension
    0.82
     Suite
    0.82
     Ext
    0.71
     STE
    0.70
     extension
    0.70
     Ste
    0.69
     suite
    0.69
    Suite
    0.68
     EXTENSION
    0.66
     SUITE
    0.66
    Activations Density 0.126%

    No Known Activations