© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4933
    Prev
    Next
    INDEX
    Explanations

    sequences of special characters or formatting elements

    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
    IUrlHelper
    -0.63
    出版年
    -0.53
     Reel
    -0.50
     Ub
    -0.49
     Tint
    -0.49
    }{*}{
    -0.49
     dere
    -0.47
     UL
    -0.47
     fau
    -0.46
    EndGlobalSection
    -0.46
    POSITIVE LOGITS
     Fassung
    0.50
     Auffassung
    0.50
     Aufstieg
    0.49
     onPostExecute
    0.48
     llorando
    0.48
     Änderung
    0.47
     Sünde
    0.46
    didSet
    0.46
     Anordnung
    0.45
     Beteiligung
    0.45
    Activations Density 0.090%

    No Known Activations