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. 113862
    Prev
    Next
    INDEX
    Explanations

    references to isolation from external influences and environments

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

    from the environment

    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
     REPRESENT
    -0.30
     atas
    -0.29
     Schweizer
    -0.29
     против
    -0.28
     תפ
    -0.28
     gegen
    -0.27
    vening
    -0.26
     Gegen
    -0.26
     Gart
    -0.26
     figure
    -0.26
    POSITIVE LOGITS
     queſta
    0.88
    tagHelperRunner
    0.79
     ब्रेकडाउन
    0.73
     يتيمه
    0.73
     وتسجيلات
    0.73
     snippetHide
    0.72
    WriteBarrier
    0.70
    iſchen
    0.70
     estekak
    0.69
    fromnode
    0.69
    Activations Density 0.045%

    No Known Activations