© 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. 38-GEMMASCOPE-RES-16K
    11. 7917
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and character names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.56
    ніципалі
    -0.43
    таратура
    -0.42
    MessageOf
    -0.39
     Apo
    -0.39
    ̎
    -0.38
    RegressionTest
    -0.38
    WriteLiteral
    -0.38
     topo
    -0.38
    }))
    -0.37
    POSITIVE LOGITS
    openConnection
    0.52
    dy
    0.47
    ified
    0.47
    ian
    0.47
     BorderRadius
    0.47
    ige
    0.46
    ition
    0.46
    ious
    0.46
     ComVisible
    0.45
    dit
    0.44
    Activations Density 0.261%

    No Known Activations