© 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. 20-GEMMASCOPE-RES-16K
    11. 173
    Prev
    Next
    INDEX
    Explanations

    emotional reactions and interactions among characters

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

    Preceding character's name

    np_acts-logits-general · gemini-2.0-flash

    facial expressions and reactions

    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
    ⓧ
    -0.47
    соль
    -0.43
     mondi
    -0.43
     pubblici
    -0.43
    地说道
    -0.42
    的说道
    -0.41
     exigences
    -0.41
     allmän
    -0.40
    kover
    -0.40
    OGND
    -0.40
    POSITIVE LOGITS
     sighed
    1.48
     chuckled
    1.40
     sighs
    1.35
     shrugged
    1.34
     sigh
    1.33
     nodded
    1.33
     frowned
    1.33
     smiled
    1.31
     chuckle
    1.31
     groaned
    1.31
    Activations Density 0.234%

    No Known Activations