© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14652
    Prev
    Next
    INDEX
    Explanations

    structured code elements and syntax within programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*---
    -0.60
    ItemBackground
    -0.58
    CloseOperation
    -0.57
     ligiloj
    -0.57
    ⓘ
    -0.55
    ConstraintMaker
    -0.54
     ब्रेकडाउन
    -0.52
    CPtr
    -0.51
    itinéraire
    -0.49
    ftagPool
    -0.49
    POSITIVE LOGITS
    :✨
    0.54
    assemblée
    0.47
    Jennifer
    0.45
     plastiques
    0.45
     stadig
    0.45
     syke
    0.43
     científicas
    0.43
     agrícolas
    0.43
    >
    0.42
     macetas
    0.41
    Activations Density 0.181%

    No Known Activations