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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16269
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to flooring and cleaning activities

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

    "floor" or "flooring"

    np_acts-logits-general · gemini-2.0-flash

    floor cleaning and materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ned
    -0.44
     Wikime
    -0.41
    Ned
    -0.41
     Confederacy
    -0.40
    blitz
    -0.38
    publicain
    -0.37
    PMailer
    -0.36
    Fruit
    -0.36
    onAttach
    -0.36
     سد
    -0.36
    POSITIVE LOGITS
     floor
    1.75
     floors
    1.63
     flooring
    1.60
     FLOOR
    1.53
     Floor
    1.50
    floor
    1.48
    Floor
    1.41
     Floors
    1.32
    floors
    1.30
    FLOOR
    1.30
    Activations Density 0.043%

    No Known Activations