© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3026
    Prev
    Next
    INDEX
    Explanations

    questions related to future possibilities and factors influencing change

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

    personal opinion or first-person perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    RectangleBorder
    -0.77
     متعلقه
    -0.66
    newswire
    -0.63
    MenuInflater
    -0.62
    InputBorder
    -0.61
     समीक्षाओं
    -0.61
    mergeFrom
    -0.60
    KommentareTeilen
    -0.60
    ImageContext
    -0.58
    DockStyle
    -0.57
    POSITIVE LOGITS
     I
    1.44
     IMO
    1.10
     IMHO
    1.05
    我觉得
    1.02
     imo
    1.02
    我覺得
    1.00
     я
    0.90
     creo
    0.88
    I
    0.88
    我认为
    0.88
    Activations Density 0.336%

    No Known Activations