© 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. 3-GEMMASCOPE-RES-16K
    11. 5756
    Prev
    Next
    INDEX
    Explanations

    markers for the beginning of significant sections or sections of text within a document

    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
     ModelExpression
    -0.93
    queryInterface
    -0.92
    ConstraintMaker
    -0.92
     AssemblyProduct
    -0.89
    featureID
    -0.86
     BoxFit
    -0.86
    parsedMessage
    -0.83
    HomeAsUpEnabled
    -0.83
    genodigd
    -0.82
    ValueStyle
    -0.82
    POSITIVE LOGITS
    例文帳に追加
    0.34
    1
    0.31
     ал
    0.24
     back
    0.23
     beg
    0.23
    ốc
    0.22
     online
    0.21
     ones
    0.21
     edit
    0.21
     information
    0.21
    Activations Density 0.312%

    No Known Activations