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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 6069
    Prev
    Next
    INDEX
    Explanations

    elements of HTML and JavaScript

    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
    readystatechange
    -0.64
    demic
    -0.55
     Lehrer
    -0.55
    enderror
    -0.55
    usermodel
    -0.54
     Elena
    -0.50
    GraphicsUnit
    -0.50
     convertView
    -0.49
    ertos
    -0.49
     Gram
    -0.49
    POSITIVE LOGITS
     ̄)
    0.75
    rdı
    0.75
    NUMX
    0.73
    afficheront
    0.73
    )++;
    0.73
    */
    
    
    0.72
     ſche
    0.72
    });
    
    
    0.71
     */
    
    
    0.70
    !")
    
    0.69
    Activations Density 0.071%

    No Known Activations