© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12696
    Prev
    Next
    INDEX
    Explanations

    start tokens and structured formatting indicators in code-like documents

    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
    󠁣
    -0.46
     tarvit
    -0.38
    ัจ
    -0.37
     Gorb
    -0.37
     voetballer
    -0.37
     Kapol
    -0.36
     läh
    -0.35
    PROLOG
    -0.35
     diputado
    -0.35
    exels
    -0.35
    POSITIVE LOGITS
    mergeFrom
    0.54
    ScopeManager
    0.52
    ldots
    0.51
    躇
    0.51
    WithIOException
    0.49
    ArrowToggle
    0.47
     상세
    0.44
     mellitus
    0.44
     arts
    0.44
     continuant
    0.44
    Activations Density 0.081%

    No Known Activations