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. 20-GEMMASCOPE-RES-16K
    6. 9772
    Prev
    Next
    INDEX
    Explanations

    comments and documentation syntax in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    extAlignment
    -1.14
     MainAxisSize
    -1.08
     }}"></
    -0.97
    `;
    
    -0.94
     saites
    -0.93
    исленность
    -0.91
     Efq
    -0.90
    Hentet
    -0.89
    NUMX
    -0.89
    '):
    
    -0.89
    POSITIVE LOGITS
    if
    0.89
    https
    0.71
    this
    0.65
    http
    0.65
    for
    0.64
    We
    0.63
    or
    0.60
    This
    0.58
        
    0.58
    Here
    0.58
    Activations Density 0.104%

    No Known Activations