© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7482
    Prev
    Next
    INDEX
    Explanations

    formal elements related to programming, particularly related to routes and actions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.47
     Савезне
    -0.42
    Portály
    -0.42
    агностика
    -0.39
     AssemblyCulture
    -0.39
     disambiguazione
    -0.38
    stateProvider
    -0.38
    migrationBuilder
    -0.38
    ifrance
    -0.37
    Portail
    -0.36
    POSITIVE LOGITS
     action
    3.89
    action
    3.30
     Action
    3.16
    Action
    3.00
     acción
    2.92
     ACTION
    2.91
     ação
    2.61
    ACTION
    2.59
     actions
    2.56
    アクション
    2.39
    Activations Density 0.798%

    No Known Activations