© 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. 6-GEMMASCOPE-RES-16K
    6. 11876
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, specifically looking for structural or functional patterns in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.55
     lò
    -0.55
    ><!--
    -0.49
     sør
    -0.48
    ↵
    -0.48
    httphttps
    -0.48
     vivas
    -0.48
    ↵↵
    -0.48
     VizieR
    -0.47
     ivelany
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.98
    enumii
    0.86
    enumi
    0.82
     Monfieur
    0.74
    endphp
    0.72
     Majefty
    0.70
    Consumes
    0.69
    TypedDataSet
    0.68
    
    0.67
     الدولى
    0.66
    Activations Density 0.099%

    No Known Activations