© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35296
    Prev
    Next
    INDEX
    Explanations

    percentage signs and their context in numerical expressions

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

    string formatting specifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.46
     in
    -0.44
    uxxxx
    -0.44
    providedIn
    -0.40
    ői
    -0.39
    ".
    
    -0.37
     pilla
    -0.37
    DCM
    -0.36
    </em>
    -0.34
     Rudi
    -0.34
    POSITIVE LOGITS
    ("%
    0.94
     %
    0.91
     ("%
    0.85
    ="%
    0.82
    ('%
    0.82
     $\%
    0.78
     "%
    0.77
     '%
    0.76
     $\%$
    0.76
     defaultstate
    0.76
    Activations Density 0.013%

    No Known Activations