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. 38867
    Prev
    Next
    INDEX
    Explanations

    specific dishes and cooking methods, particularly related to poultry and other meats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ब्रेकडाउन
    -0.59
     &___
    -0.54
    BibitemShut
    -0.47
    ureux
    -0.44
    HasAnnotation
    -0.44
    migrationBuilder
    -0.43
    VertexAttrib
    -0.43
     Paglinawan
    -0.41
    tapete
    -0.41
    quần
    -0.41
    POSITIVE LOGITS
    sizeCache
    0.42
    
    0.40
     виправивши
    0.39
    ModelForm
    0.38
    tisserie
    0.37
    DrawerToggle
    0.37
    setContentView
    0.36
     boek
    0.36
    weightedMode
    0.35
    انتهای
    0.35
    Activations Density 0.022%

    No Known Activations