© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 4949
    Prev
    Next
    INDEX
    Explanations

    Python programming keywords and function definitions within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.20
    HomeAsUpEnabled
    -1.08
     Beſ
    -1.00
     BoxFit
    -1.00
     Monfieur
    -0.99
     onOptions
    -0.95
    basicConfig
    -0.94
    parsedMessage
    -0.93
    enumii
    -0.92
     Partagez
    -0.91
    POSITIVE LOGITS
    ;
    0.65
     
    0.52
    ,
    0.50
    */
    0.48
     v
    0.47
     s
    0.47
    /*
    0.45
     ;
    0.43
    //
    0.43
     to
    0.43
    Activations Density 0.412%

    No Known Activations