© 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. 18-GEMMASCOPE-RES-16K
    11. 52
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion and facial reactions in characters

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

    facial expressions

    np_acts-logits-general · gemini-2.0-flash

    facial expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.66
    expandindo
    -0.65
    esModule
    -0.60
     odkazy
    -0.56
    ьаж
    -0.56
    esez
    -0.55
    اتا
    -0.54
    libft
    -0.53
    AddTagHelper
    -0.51
     Réponses
    -0.51
    POSITIVE LOGITS
     expression
    1.53
     faces
    1.47
     expressions
    1.42
     face
    1.36
     facial
    1.36
     Expression
    1.32
    expression
    1.32
     Expressions
    1.26
    Expression
    1.25
    faces
    1.20
    Activations Density 0.094%

    No Known Activations