© 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. 11-GEMMASCOPE-RES-16K
    11. 4291
    Prev
    Next
    INDEX
    Explanations

    references to data fields and their structures in programming or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onus
    -0.57
     Swanson
    -0.56
     Constipation
    -0.54
     Abubakar
    -0.53
    poptosis
    -0.52
    addto
    -0.52
     Caron
    -0.51
    onSave
    -0.50
    EDEFAULT
    -0.50
     McN
    -0.50
    POSITIVE LOGITS
     field
    2.05
    Field
    1.94
     Field
    1.93
    field
    1.79
     FIELD
    1.77
     fields
    1.68
     Fields
    1.63
    FIELD
    1.62
    Fields
    1.57
    fields
    1.54
    Activations Density 0.121%

    No Known Activations