© 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. 84084
    Prev
    Next
    INDEX
    Explanations

    names, particularly those with the name "Zah" or variants of "Ahmed" and "Isaac"

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

    names

    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
    HomeAsUpEnabled
    -0.66
     nahilalakip
    -0.49
    StatusOK
    -0.48
     Osorio
    -0.46
     migrator
    -0.46
     Boven
    -0.44
     StatefulWidget
    -0.43
    Slf
    -0.43
     Channel
    -0.43
    Spoljašnje
    -0.43
    POSITIVE LOGITS
    OGND
    0.63
    agoza
    0.63
    NotEmpty
    0.53
    penters
    0.53
    bicycle
    0.52
    nologies
    0.51
    Bicycle
    0.51
    orghini
    0.50
     Barber
    0.50
    świ
    0.50
    Activations Density 0.056%

    No Known Activations