© 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. 16263
    Prev
    Next
    INDEX
    Explanations

    specific programming languages, protocols, or structured data specifications

    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
     prohibido
    -0.43
     Nachbarn
    -0.43
     commandés
    -0.39
     refusé
    -0.39
     marié
    -0.38
     NACIONAL
    -0.38
     mencionado
    -0.38
     cumplido
    -0.38
    Membership
    -0.36
     CanadaChoose
    -0.36
    POSITIVE LOGITS
    Personendaten
    0.62
     <>",
    0.59
     noqa
    0.57
    Ifc
    0.56
    $_['
    0.55
     OAuth
    0.52
     NVMe
    0.51
    apatalk
    0.50
    jectory
    0.50
    fhir
    0.50
    Activations Density 0.845%

    No Known Activations