© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 11128
    Prev
    Next
    INDEX
    Explanations

    references to facial expressions or the concept of a "face."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelAdmin
    -0.59
     priorité
    -0.55
     уважением
    -0.55
    pricht
    -0.53
    newBuilder
    -0.53
    StreetMap
    -0.53
    rawDesc
    -0.52
     pensato
    -0.52
     domésticos
    -0.51
    ---*/
    -0.51
    POSITIVE LOGITS
     face
    5.09
     Face
    4.49
    face
    4.42
    Face
    4.37
     faces
    4.13
     FACE
    4.02
    FACE
    3.78
    faces
    3.46
     Faces
    3.34
     faced
    3.13
    Activations Density 0.049%

    No Known Activations