© 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 EvalsExportsAPI 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. 55274
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "chocolate"

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

    chocolate and chocolates

    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
     Geral
    -0.50
     PublicKey
    -0.46
     împre
    -0.45
     direta
    -0.45
     rifer
    -0.45
     jesteś
    -0.45
    logous
    -0.44
     attuale
    -0.44
     wikipagina
    -0.44
     Surveyor
    -0.43
    POSITIVE LOGITS
     Chocolate
    1.22
    Chocolate
    1.21
     chocolate
    1.17
    chocolate
    1.08
    OCOLATE
    1.01
     chocolat
    0.89
     chocolates
    0.85
    colates
    0.85
     chocol
    0.82
     cioccolato
    0.72
    Activations Density 0.007%

    No Known Activations