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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5491
    Prev
    Next
    INDEX
    Explanations

    coding structures and syntax related to programming logic and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ACCOM
    -0.44
     freddo
    -0.42
     Cranston
    -0.42
    jsko
    -0.41
     rispar
    -0.40
     tiks
    -0.40
    routeProvider
    -0.40
     CanadaChoose
    -0.40
     onlyOwner
    -0.40
     Италијани
    -0.39
    POSITIVE LOGITS
    ScopeManager
    0.55
     juger
    0.50
     exame
    0.48
     xem
    0.45
    EndContext
    0.44
    RuleContext
    0.42
     examined
    0.41
    Гео
    0.41
     judged
    0.41
     evaluated
    0.39
    Activations Density 0.517%

    No Known Activations