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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45747
    Prev
    Next
    INDEX
    Explanations

    PHP code structure and control flow elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    PHP loop and template delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     الحره
    -0.72
     AssemblyTitle
    -0.68
    новништво
    -0.68
    səhifə
    -0.67
    AnimationsModule
    -0.66
    lapsingToolbar
    -0.63
    ://$
    -0.60
    ſelf
    -0.57
    verifyException
    -0.57
     الاطلاع
    -0.57
    POSITIVE LOGITS
     onBind
    0.28
     correctes
    0.26
    <?=
    0.26
    []}
    0.26
    WillAppear
    0.24
     pungkas
    0.24
    NM
    0.23
     lẻ
    0.23
     Yer
    0.22
     coster
    0.22
    Activations Density 0.003%

    No Known Activations