Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 45951
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements typically used in programming or markup languages

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

    missense mutations

    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
    tagHelperRunner
    -0.60
     fermés
    -0.54
    providedIn
    -0.51
     prêtres
    -0.50
     financières
    -0.50
    serviceWorker
    -0.48
     juridiques
    -0.48
     industriels
    -0.48
     prépar
    -0.46
    translator
    -0.46
    POSITIVE LOGITS
    ('/:
    1.22
    ("/:
    1.13
    /:
    1.05
     useParams
    0.56
    [:
    0.55
    =:
    0.54
     AssemblyCompany
    0.53
     campsite
    0.53
    (?:
    0.52
     \#:
    0.52
    Activations Density 0.000%

    No Known Activations