© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 78288
    Prev
    Next
    INDEX
    Explanations

    coding syntax elements and punctuation marks

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

    code/math punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -1.16
    rungsseite
    -1.07
    __':
    -0.98
    featureID
    -0.97
     Мексичка
    -0.94
    fjspx
    -0.93
     propOrder
    -0.91
    ")));
    -0.88
     autorytatywna
    -0.87
    MigrationBuilder
    -0.87
    POSITIVE LOGITS
    .
    0.67
    ,
    0.53
    ;
    0.46
     cromado
    0.42
     .
    0.37
    .,
    0.37
     when
    0.36
    ).
    0.36
     Futter
    0.34
    )
    0.33
    Activations Density 0.109%

    No Known Activations