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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 13422
    Prev
    Next
    INDEX
    Explanations

    patterns in code structure and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.57
    StoreMessageInfo
    -0.54
    onViewCreated
    -0.53
    entiated
    -0.52
     Rigby
    -0.52
    ğlık
    -0.52
     समीक्षक
    -0.51
     EnglishChoose
    -0.51
    intahan
    -0.50
    AccessorTable
    -0.50
    POSITIVE LOGITS
     InputDecoration
    0.68
     than
    0.58
     للاسماء
    0.56
    ListItemIcon
    0.52
     Then
    0.52
    clerview
    0.51
    AndPassword
    0.49
     then
    0.49
    CompleteListener
    0.49
    jątk
    0.49
    Activations Density 0.040%

    No Known Activations