© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3815
    Prev
    Next
    INDEX
    Explanations

    instances of interaction or conflict between people

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

    "face" follows certain words

    np_acts-logits-general · gemini-2.0-flash

    face and faces

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    معلومات
    -0.63
     Meksiku
    -0.54
    下载附件
    -0.52
    toks
    -0.51
    sumi
    -0.48
    msgTypes
    -0.48
     sánh
    -0.47
    ViewImports
    -0.47
    tagHelperRunner
    -0.47
    ಂದು
    -0.46
    POSITIVE LOGITS
     face
    2.71
     faces
    2.52
    face
    2.23
     Face
    2.16
    Face
    2.14
     FACE
    2.02
    faces
    1.97
     Faces
    1.95
     faced
    1.83
    FACE
    1.82
    Activations Density 0.204%

    No Known Activations