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. 91466
    Prev
    Next
    INDEX
    Explanations

    terms related to materials and coatings in technical contexts

    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
    tvguidetime
    -0.57
     surla
    -0.54
    saraba
    -0.53
    RegressionTest
    -0.48
     isNameExpr
    -0.46
    lorum
    -0.46
    tagHelperRunner
    -0.44
     Hann
    -0.44
    icale
    -0.42
    rungsseite
    -0.41
    POSITIVE LOGITS
     BIBSYS
    0.47
    ismet
    0.45
    Autoritní
    0.43
     جلوگیری
    0.39
    AnimationsModule
    0.39
    ModelAdmin
    0.38
     répondit
    0.37
     safeguards
    0.37
     prevent
    0.36
    Styleable
    0.36
    Activations Density 0.078%

    No Known Activations