© 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. 20-GEMMASCOPE-RES-16K
    11. 7525
    Prev
    Next
    INDEX
    Explanations

    code structures related to class and state management in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.77
     utafitiHapana
    -0.65
    featureID
    -0.63
    StoreMessageInfo
    -0.63
     saveiro
    -0.54
     $_(
    -0.53
     ſind
    -0.51
     plufieurs
    -0.49
    VYMaps
    -0.48
    RenderAtEndOf
    -0.46
    POSITIVE LOGITS
     formally
    0.43
    ondissement
    0.42
     insuffisamment
    0.41
     otherwise
    0.40
     also
    0.38
     moreover
    0.38
     recogn
    0.38
    󠁴
    0.37
     systematically
    0.37
     too
    0.36
    Activations Density 0.265%

    No Known Activations