© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102620
    Prev
    Next
    INDEX
    Explanations

    elements of HTML ordered lists and their items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Décès
    -0.70
    rungsseite
    -0.69
    setVerticalGroup
    -0.65
    +#+
    -0.64
    +#+#
    -0.60
    keyColumn
    -0.59
    новништво
    -0.59
     snippetHide
    -0.58
     lenker
    -0.58
    EndContext
    -0.58
    POSITIVE LOGITS
     kaarangay
    0.35
     organ
    0.33
     pin
    0.31
     capac
    0.31
     activation
    0.30
    iyor
    0.29
    waltung
    0.29
    ступила
    0.29
     Activation
    0.29
     Paglinawan
    0.28
    Activations Density 0.101%

    No Known Activations