© 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. 4298
    Prev
    Next
    INDEX
    Explanations

    structured dialogue and exchanges between characters

    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
     tand
    -0.33
     Res
    -0.32
     أس
    -0.31
    砺
    -0.31
    getWriter
    -0.31
     pres
    -0.30
    FW
    -0.30
     fakt
    -0.29
    reuung
    -0.28
    camiento
    -0.28
    POSITIVE LOGITS
     Administrativna
    0.75
     مشين
    0.73
     ब्रेकडाउन
    0.67
    GOTREF
    0.65
    Дереккөздер
    0.64
    Autoritní
    0.63
    GEBURTSDATUM
    0.61
     cherchés
    0.59
    complexContent
    0.57
     kaarangay
    0.57
    Activations Density 0.108%

    No Known Activations