© 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. 15366
    Prev
    Next
    INDEX
    Explanations

    attributes of aesthetic appreciation and complimenting visuals

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

    Preceding "is," "was," or "?"

    np_acts-logits-general · gemini-2.0-flash

    cute baby girl

    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
    ̍t
    -0.63
    Solución
    -0.60
    rawtypes
    -0.60
     Comprometido
    -0.59
    mnop
    -0.57
    licet
    -0.57
    |--
    -0.56
    IsContent
    -0.56
     Diſ
    -0.56
    UnknownFieldSet
    -0.56
    POSITIVE LOGITS
     cute
    1.61
     adorable
    1.61
     cutest
    1.58
     Adorable
    1.43
    Cute
    1.43
     Cute
    1.41
    adorable
    1.41
    Adorable
    1.39
     CUTE
    1.35
    cute
    1.23
    Activations Density 0.138%

    No Known Activations