© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15573
    Prev
    Next
    INDEX
    Explanations

    commands or functions related to validation checks

    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
     voordeel
    -0.46
    一双
    -0.43
    getMinutes
    -0.41
     publiek
    -0.40
     newUser
    -0.39
    void
    -0.39
     getResources
    -0.38
     parentId
    -0.38
     demais
    -0.37
     płyn
    -0.37
    POSITIVE LOGITS
     check
    2.61
     Check
    2.50
    check
    2.39
    Check
    2.36
     CHECK
    2.25
     checks
    2.11
     Checks
    2.02
    CHECK
    2.00
     checked
    1.99
     checking
    1.95
    Activations Density 0.070%

    No Known Activations