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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 14530
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols often associated with emphasis or transition in text

    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
    aarrggbb
    -0.69
     Meksiku
    -0.65
    LError
    -0.63
     Carrington
    -0.61
    ه
    -0.59
    //}
    
    -0.58
    HandlerContext
    -0.58
    ΡΙ
    -0.57
    ellido
    -0.56
     Teller
    -0.55
    POSITIVE LOGITS
    Архівовано
    0.99
    Tembelea
    0.90
     piú
    0.81
    
    0.80
     */
    
    
    0.78
    */
    
    
    0.77
    });
    
    
    0.75
     vnto
    0.71
    ագրություններ
    0.69
    ConstraintMaker
    0.69
    Activations Density 0.517%

    No Known Activations