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. 4689
    Prev
    Next
    INDEX
    Explanations

    mentions of specific sports players and their performance statistics

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

    scores or scoring

    np_acts-logits-general · gemini-2.0-flash

    effect of

    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
     médecins
    -0.53
     naturelles
    -0.53
    ⓘ
    -0.52
    ровень
    -0.50
    InsertCommand
    -0.50
    ########.
    -0.48
     wanton
    -0.48
     sauvages
    -0.48
    jala
    -0.46
     esportes
    -0.46
    POSITIVE LOGITS
     Савезне
    0.73
     score
    0.68
     scores
    0.66
    )"),
    0.64
     SCORE
    0.63
     Contributions
    0.63
     scored
    0.62
    tvguidetime
    0.62
    ConstraintMaker
    0.60
     contributions
    0.60
    Activations Density 0.079%

    No Known Activations