© 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. 14617
    Prev
    Next
    INDEX
    Explanations

    references to physical attributes or measurements of individuals, particularly athletes

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

    following "pound", "tackle", or "("

    np_acts-logits-general · gemini-2.0-flash

    heavyweight giant

    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
     spion
    -0.54
     small
    -0.51
     tiny
    -0.51
     papillon
    -0.51
    Small
    -0.48
     pochette
    -0.47
     mikro
    -0.46
     små
    -0.46
     piccolo
    -0.46
     μικ
    -0.45
    POSITIVE LOGITS
     behe
    1.34
     giant
    1.30
     gigantic
    1.19
    giant
    1.17
     heavyweight
    1.17
     mammoth
    1.13
     gigante
    1.12
     Giant
    1.10
    Giant
    1.10
     colossal
    1.07
    Activations Density 0.278%

    No Known Activations