Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13810
    Prev
    Next
    INDEX
    Explanations

    references to the word "foot" in various contexts

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

    "foot" and related words

    np_acts-logits-general · gemini-2.0-flash

    foot, feet, footprint, footwork

    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
     indisponible
    -0.49
    iedene
    -0.48
     existing
    -0.45
    Parameterized
    -0.44
     langs
    -0.44
    existing
    -0.43
    خاذ
    -0.42
    quested
    -0.42
     manual
    -0.42
    rijke
    -0.42
    POSITIVE LOGITS
     Foot
    1.00
     Feet
    0.98
     foot
    0.95
     FOOT
    0.93
     feet
    0.93
    Foot
    0.91
    SequentialGroup
    0.91
     FEET
    0.90
    feet
    0.89
    Feet
    0.88
    Activations Density 0.076%

    No Known Activations