© 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. 24-GEMMASCOPE-RES-16K
    11. 4697
    Prev
    Next
    INDEX
    Explanations

    elements related to emotions and human connections in narratives

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

    after adjectives of appearance

    np_acts-logits-general · gemini-2.0-flash

    descriptive appearance, style, or scenery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.83
     للاسماء
    -0.74
    migrationBuilder
    -0.70
    UserScript
    -0.69
     doInBackground
    -0.68
    :✨
    -0.67
    writeFieldEnd
    -0.66
    ंदीखरीदारी
    -0.64
    makeConstraints
    -0.63
     ExecuteAsync
    -0.62
    POSITIVE LOGITS
     temperament
    0.61
     outlines
    0.59
     style
    0.58
     stijl
    0.57
     elegant
    0.56
     vicissitudes
    0.55
     solemn
    0.55
     nob
    0.54
     reveals
    0.53
     exquis
    0.53
    Activations Density 0.060%

    No Known Activations