© 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. 15377
    Prev
    Next
    INDEX
    Explanations

    details related to workout formats and exercise routines

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

    after "by", "of", "the", and "I"

    np_acts-logits-general · gemini-2.0-flash

    physical strength and exercise

    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
    HomeAsUpEnabled
    -0.54
    igator
    -0.51
     Signalez
    -0.47
    __*/
    -0.46
     Ind
    -0.45
    芒
    -0.45
     Midsummer
    -0.44
    styleType
    -0.44
    spender
    -0.43
    Organisateur
    -0.43
    POSITIVE LOGITS
     barbell
    1.10
     weights
    1.02
     weight
    0.88
    lifting
    0.87
     lifting
    0.86
     Weights
    0.85
     dumbbells
    0.81
    Weights
    0.81
    weights
    0.81
     dumbbell
    0.80
    Activations Density 0.112%

    No Known Activations