© 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. 13468
    Prev
    Next
    INDEX
    Explanations

    structured data or code snippets related to API responses and state management

    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
    /*
    -0.62
     estekak
    -0.54
     AssemblyTitle
    -0.50
     Roskov
    -0.49
    delwed
    -0.49
    ğraf
    -0.48
     tslint
    -0.48
    IVEREF
    -0.46
    saraba
    -0.45
    hatenablog
    -0.45
    POSITIVE LOGITS
     props
    0.74
    props
    0.73
    handle
    0.73
    useEffect
    0.73
     handle
    0.73
    formik
    0.71
    dispatch
    0.68
     useEffect
    0.65
     dispatch
    0.64
    Props
    0.63
    Activations Density 0.076%

    No Known Activations