© 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. 37-GEMMASCOPE-RES-16K
    11. 4002
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     widow
    -0.33
     Mullins
    -0.33
     Comentarios
    -0.31
     liber
    -0.30
     leña
    -0.29
    Literatuur
    -0.29
     HST
    -0.29
     Schwim
    -0.29
    เอา
    -0.29
     breakfast
    -0.29
    POSITIVE LOGITS
     Fargo
    0.91
     Bismarck
    0.80
     ND
    0.75
     UND
    0.70
    Moor
    0.63
    ND
    0.62
    RenderAtEndOf
    0.62
     Moor
    0.59
    SourceChecksum
    0.59
    SpringRunner
    0.59
    Activations Density 0.191%

    No Known Activations