© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 54259
    Prev
    Next
    INDEX
    Explanations

    references to a specific character or theme related to a film or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    スリーパー関連

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     vrijwilli
    -0.49
     idéia
    -0.44
     aanv
    -0.43
     osallist
    -0.43
     judíos
    -0.43
     débil
    -0.42
     discí
    -0.42
     eenvou
    -0.42
     Evangelio
    -0.41
     disfraces
    -0.41
    POSITIVE LOGITS
    transQ
    0.74
     ObjectParameter
    0.69
    featureID
    0.69
    URLException
    0.68
     ſche
    0.67
     itſelf
    0.67
     queſta
    0.66
    parsedMessage
    0.66
     للمعارف
    0.65
     ſte
    0.64
    Activations Density 0.014%

    No Known Activations