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. 10023
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and methodologies

    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
     kollu
    -0.61
     doInBackground
    -0.56
     doigt
    -0.55
    itemBuilder
    -0.54
     commonest
    -0.54
     Satisfied
    -0.53
    ágok
    -0.53
    ↳
    -0.53
     stessi
    -0.53
     tasche
    -0.51
    POSITIVE LOGITS
    exitRule
    0.70
    جستارهای
    0.69
     resourceCulture
    0.68
    ViewFeatures
    0.67
    typeorm
    0.67
    ("}");
    0.66
     ويكيپيديا
    0.66
    úncia
    0.62
    nestjs
    0.62
    PerformLayout
    0.61
    Activations Density 1.044%

    No Known Activations