© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 83890
    Prev
    Next
    INDEX
    Explanations

    references to historical accounts and analyses

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

    biographies and historical accounts

    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
    abello
    -0.44
     hoek
    -0.43
    verständ
    -0.42
    berday
    -0.41
    værende
    -0.40
     Universitaria
    -0.40
    XMLSchema
    -0.40
    ulihan
    -0.40
     Sunflower
    -0.40
    schw
    -0.39
    POSITIVE LOGITS
    Personensuche
    0.45
     history
    0.43
    PostInfinity
    0.42
     historians
    0.42
    tangentMode
    0.41
     fascinating
    0.40
    RequestParam
    0.39
     historical
    0.39
    artifactId
    0.38
    CardHeader
    0.38
    Activations Density 0.035%

    No Known Activations