© 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. 3-GEMMASCOPE-RES-16K
    6. 8770
    Prev
    Next
    INDEX
    Explanations

    HTML list and link elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useState
    -0.54
    yntaxException
    -0.51
    useState
    -0.51
    ">@
    -0.47
    $_['
    -0.46
    CodeAnalysis
    -0.44
     bào
    -0.44
    queryInterface
    -0.44
    setCellValue
    -0.43
    LLocation
    -0.42
    POSITIVE LOGITS
    ul
    0.57
    <tfoot>
    0.56
    mtable
    0.52
    </thead>
    0.51
    ="#"
    0.49
     nakalista
    0.48
    complexContent
    0.46
     redacción
    0.45
    <thead>
    0.45
     cellspacing
    0.45
    Activations Density 0.225%

    No Known Activations