© 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. 5-GEMMASCOPE-RES-16K
    6. 8210
    Prev
    Next
    INDEX
    Explanations

    occurrences of JavaScript syntax and comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ه
    -1.03
     Bep
    -0.81
     Amos
    -0.80
    Amos
    -0.79
    twimg
    -0.78
     Nicolson
    -0.77
     Stowe
    -0.73
    มาะ
    -0.73
    Dora
    -0.71
    ва
    -0.71
    POSITIVE LOGITS
    ()]
    
    0.98
    VIAF
    0.96
    ····
    0.91
    opat
    0.86
    /**
    
    0.84
     TextInputType
    0.83
    migrationBuilder
    0.83
     aceit
    0.82
    bezpiecz
    0.81
    >";
    
    0.81
    Activations Density 0.066%

    No Known Activations