© 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. 9211
    Prev
    Next
    INDEX
    Explanations

    functions that manipulate data structures

    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
    Personensuche
    -0.52
     المعيارى
    -0.48
     pié
    -0.46
    最快更新
    -0.45
    }{*}{}
    -0.44
     helicópter
    -0.43
     vacunación
    -0.43
     redé
    -0.43
     maquin
    -0.42
     individuos
    -0.42
    POSITIVE LOGITS
    printStackTrace
    0.63
    arraycopy
    0.63
    forEach
    0.61
    setopt
    0.59
    fromCharCode
    0.58
    ResumeLayout
    0.57
    equals
    0.57
    stringify
    0.56
    SerializedName
    0.56
    putExtra
    0.55
    Activations Density 0.127%

    No Known Activations