© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 16328
    Prev
    Next
    INDEX
    Explanations

    expressions of authority and emotional responses in dialogue

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

    Facial expressions or gazes

    np_acts-logits-general · gemini-2.0-flash

    facial expressions and gaze

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.85
    TagMode
    -0.78
    VersionUID
    -0.73
    Portail
    -0.65
    ItemLayout
    -0.65
    esModule
    -0.64
     dAtA
    -0.64
    ChildScrollView
    -0.63
    homonymie
    -0.63
    providedIn
    -0.63
    POSITIVE LOGITS
     expression
    0.66
     jakby
    0.54
    expression
    0.53
     gefährlich
    0.52
     meres
    0.51
     conveying
    0.49
     fixed
    0.49
     duidelijk
    0.49
     menace
    0.49
     challenge
    0.49
    Activations Density 0.111%

    No Known Activations