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. 120251
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of machinery or components

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

    mechanical components and their function

    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
    LookAnd
    -0.80
    httphttps
    -0.60
    adaptiveStyles
    -0.57
    ⓧ
    -0.55
     مشين
    -0.54
    Diweddarwch
    -0.54
    endphp
    -0.51
    DockStyle
    -0.50
    SharedDtor
    -0.49
    ViewFeatures
    -0.48
    POSITIVE LOGITS
     ensures
    0.44
     ensure
    0.42
     garantiza
    0.42
     renfor
    0.40
     optional
    0.39
    ModelSerializer
    0.39
     avviene
    0.38
     allows
    0.38
     built
    0.38
     permettent
    0.38
    Activations Density 0.028%

    No Known Activations