© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 5961
    Prev
    Next
    INDEX
    Explanations

    references to "foot" in various contexts

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

    "foot" and related terms

    np_acts-logits-general · gemini-2.0-flash

    foot and compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iedene
    -0.51
    Parameterized
    -0.51
    “
    -0.44
     “
    -0.44
    rijke
    -0.43
    jef
    -0.42
    жал
    -0.41
     O
    -0.41
    事了
    -0.41
    ,
    -0.40
    POSITIVE LOGITS
     Foot
    1.21
     Feet
    1.18
     foot
    1.14
     feet
    1.14
     FOOT
    1.14
    Foot
    1.11
    Feet
    1.09
    feet
    1.05
     FEET
    1.03
     Footwear
    1.01
    Activations Density 0.148%

    No Known Activations