© 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. 0-GEMMASCOPE-RES-16K
    11. 8782
    Prev
    Next
    INDEX
    Explanations

    terms related to specification and standards in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exitRule
    -0.60
    RenderAtEndOf
    -0.52
    Билгалдахарш
    -0.47
     surla
    -0.47
     poveznice
    -0.46
    ">//
    -0.46
    TagMode
    -0.46
     EconPapers
    -0.46
    gación
    -0.46
    Искәрмәләр
    -0.45
    POSITIVE LOGITS
     Diver
    0.77
     spec
    0.77
     DIVERS
    0.71
    Diver
    0.71
     Spec
    0.70
    Spec
    0.69
     substituted
    0.68
     diversify
    0.66
     diversi
    0.65
    spec
    0.62
    Activations Density 1.766%

    No Known Activations