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. 22-GEMMASCOPE-RES-16K
    6. 14031
    Prev
    Next
    INDEX
    Explanations

    elements related to component structure and styling in web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     at
    -0.56
    ,
    -0.53
     ob
    -0.50
    ↵↵
    -0.49
     pic
    -0.46
    Przypisy
    -0.45
    AddAttribute
    -0.45
     At
    -0.45
     close
    -0.45
     ,
    -0.44
    POSITIVE LOGITS
    ſelf
    0.79
     Chriftian
    0.75
     ſeveral
    0.74
     itſelf
    0.69
     виправивши
    0.67
    NewUrlParser
    0.66
     pleaſure
    0.66
     estekak
    0.65
     Anſ
    0.65
     Majefty
    0.65
    Activations Density 0.120%

    No Known Activations