Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 887
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate quotations or dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )";
    
    -0.54
    _|
    -0.51
    ssa
    -0.50
     ?>/
    -0.50
     erop
    -0.49
    ']
    
    -0.49
    £
    -0.47
    ()")
    -0.46
    ()]
    
    -0.46
    "]
    
    -0.45
    POSITIVE LOGITS
    ️
    0.75
    AndEndTag
    0.73
    BrowserModule
    0.70
    RectangleBorder
    0.69
     /\.(
    0.68
    MessageOf
    0.66
     BorderRadius
    0.65
    principalColumn
    0.64
    ernalia
    0.64
     consultato
    0.63
    Activations Density 1.621%

    No Known Activations