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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-GEMMASCOPE-RES-16K
    6. 5272
    Prev
    Next
    INDEX
    Explanations

    programming function definitions and related structure in code

    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
    IsContent
    -0.88
     '\\;'
    -0.80
     الدولى
    -0.71
     [],
    
    -0.69
    ContentAsync
    -0.66
    peen
    -0.65
    Бахар
    -0.63
    extAlignment
    -0.62
    //{
    
    -0.60
    TacToe
    -0.60
    POSITIVE LOGITS
    newcommand
    1.33
    WebServlet
    0.72
    jooq
    0.64
    renewcommand
    0.63
    providedIn
    0.59
    NewUrlParser
    0.57
    presso
    0.56
    usercontent
    0.56
     kiệm
    0.55
    ########.
    0.54
    Activations Density 0.012%

    No Known Activations