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. 30325
    Prev
    Next
    INDEX
    Explanations

    occurrences of commonly used variable or function names in programming contexts

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

    math formatting `mkern`

    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
     Pulver
    -0.47
    Bibliographie
    -0.47
     Protocol
    -0.44
     Protocols
    -0.44
     пола
    -0.44
    Referencias
    -0.43
     Recipes
    -0.43
     Procedures
    -0.43
    Ingredienti
    -0.42
    よろしくお願いいたします
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    0.71
    󠁴
    0.63
    AccessorTable
    0.62
     فريبيس
    0.61
     كومونز
    0.59
     Chwiliwch
    0.55
    bootstrapcdn
    0.54
    addPreferredGap
    0.50
    VIAF
    0.49
     tartalomajánló
    0.49
    Activations Density 0.054%

    No Known Activations