© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 16054
    Prev
    Next
    INDEX
    Explanations

    requests for guidance or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEE
    -0.51
    sidemargin
    -0.48
     Biôgrafia
    -0.48
     للاسماء
    -0.48
    DockStyle
    -0.47
     שוליים
    -0.47
    RegressionTest
    -0.47
     ModelExpression
    -0.43
    enterOuterAlt
    -0.41
    contentLoaded
    -0.41
    POSITIVE LOGITS
     suggestions
    1.22
     advice
    1.17
     recommendations
    1.16
     guidance
    1.15
    Guidance
    1.07
    Suggestions
    1.05
     Suggestions
    1.05
    suggestions
    1.04
     ADVICE
    1.03
     Advice
    1.00
    Activations Density 0.364%

    No Known Activations