© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4049
    Prev
    Next
    INDEX
    Explanations

    code syntax elements and AngularJS related constructs

    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
    лтемелер
    -0.41
     <>",
    -0.38
     lenker
    -0.37
     يتيمه
    -0.37
    jsxFileName
    -0.34
    OCCURRED
    -0.34
    TacToe
    -0.33
    theoremstyle
    -0.33
    abbaye
    -0.32
    openhauer
    -0.31
    POSITIVE LOGITS
    setState
    0.64
    props
    0.63
    refs
    0.62
     setState
    0.52
     props
    0.50
    parsedMessage
    0.50
    rawDesc
    0.49
    interval
    0.48
    timeout
    0.47
    detectChanges
    0.47
    Activations Density 0.143%

    No Known Activations