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. 24459
    Prev
    Next
    INDEX
    Explanations

    syntax and structure elements in programming code

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

    Collect the terms

    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
     CreateTagHelper
    -0.71
    ReusableCell
    -0.61
    jsonwebtoken
    -0.56
    RenderAtEndOf
    -0.53
    setViewportView
    -0.52
    Scénario
    -0.52
    rungsseite
    -0.52
    AddTagHelper
    -0.51
    Hentet
    -0.50
    classnames
    -0.50
    POSITIVE LOGITS
    malla
    0.36
    GenerationType
    0.36
    avelmente
    0.35
     avena
    0.35
    providedIn
    0.35
     faveur
    0.35
    ItemBackground
    0.34
     domestiques
    0.34
     kasarigan
    0.33
    mobileqq
    0.33
    Activations Density 0.038%

    No Known Activations