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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 120838
    Prev
    Next
    INDEX
    Explanations

    terms related to web request options and configurations

    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
     AssemblyCulture
    -0.66
     ModelRenderer
    -0.64
     متعلقه
    -0.63
    IContainer
    -0.61
     فريبيس
    -0.60
    makeConstraints
    -0.59
    ConstraintMaker
    -0.57
     viewDidLoad
    -0.57
    transQ
    -0.56
     agrí
    -0.55
    POSITIVE LOGITS
    withCredentials
    0.75
    credentials
    0.49
    Credentials
    0.41
    Izvori
    0.32
     Credentials
    0.31
     terbatas
    0.30
     credentials
    0.30
    eqref
    0.30
    stopPropagation
    0.30
    secrets
    0.29
    Activations Density 0.002%

    No Known Activations