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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 6356
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inclusion or specification of items or details

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

    words that include or comprise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ETHING
    -0.34
    Iden
    -0.33
     способом
    -0.33
     yên
    -0.30
    ftrag
    -0.30
    WebpackPlugin
    -0.30
    Erstellt
    -0.29
    反
    -0.29
    Uno
    -0.29
    findById
    -0.28
    POSITIVE LOGITS
     includes
    0.93
    包括
    0.87
     include
    0.86
     included
    0.81
     Includes
    0.79
     incluye
    0.79
    includes
    0.78
     Included
    0.77
    Included
    0.75
     including
    0.75
    Activations Density 0.048%

    No Known Activations