© 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. 7-GEMMASCOPE-RES-16K
    11. 15996
    Prev
    Next
    INDEX
    Explanations

    elements related to URLs and web addresses

    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
    InjectAttribute
    -0.62
    Искәрмәләр
    -0.60
     ſever
    -0.56
     ſch
    -0.56
     ſche
    -0.55
    niſſe
    -0.55
    Quotes
    -0.54
     diſt
    -0.54
     $_(
    -0.53
    setDo
    -0.52
    POSITIVE LOGITS
     toalha
    0.33
    endpush
    0.32
     Vergrößern
    0.31
     defaultstate
    0.30
     turquesa
    0.30
     Signalez
    0.29
    ientôt
    0.28
     snippetHide
    0.28
     plateado
    0.28
     Reisedaten
    0.27
    Activations Density 1.362%

    No Known Activations