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. 4908
    Prev
    Next
    INDEX
    Explanations

    terms related to physical actions involving falls and body positions

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

    "floor" or "ground"

    np_acts-logits-general · gemini-2.0-flash

    ground or floor

    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
     cref
    -0.55
     gills
    -0.54
    rsiniz
    -0.51
     nodeId
    -0.49
     silos
    -0.49
    //
    -0.49
     Administrativna
    -0.48
     ujednoznacz
    -0.47
     dend
    -0.47
    dend
    -0.46
    POSITIVE LOGITS
     ground
    2.07
     floor
    1.97
    ground
    1.81
    Ground
    1.66
     Ground
    1.66
    floor
    1.62
     GROUND
    1.60
     Floor
    1.58
     FLOOR
    1.53
    Floor
    1.49
    Activations Density 0.157%

    No Known Activations