© 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. 9817
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting marks that often occur in written content

    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
    uestamente
    -0.39
    OVID
    -0.38
     Stelle
    -0.37
     đây
    -0.37
    ̍t
    -0.35
     zab
    -0.34
    ranti
    -0.32
    ղ
    -0.31
    wur
    -0.30
    mentar
    -0.30
    POSITIVE LOGITS
    principalTable
    0.80
    ❋
    0.77
    consulté
    0.66
     &___
    0.66
    VersionUID
    0.63
    setViewportView
    0.63
    writeFieldEnd
    0.59
    verifyException
    0.59
    enderror
    0.59
     consultato
    0.59
    Activations Density 0.173%

    No Known Activations