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. 2444
    Prev
    Next
    INDEX
    Explanations

    words related to specific entities, particularly those pertinent to illnesses and diseases

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

    starting with "Tox", "Tok", or "Tol"

    np_acts-logits-general · gemini-2.0-flash

    *Toxoplasma* infection

    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
    cerely
    -0.53
    emde
    -0.48
    ograma
    -0.47
     initComponents
    -0.44
    érique
    -0.42
    unmodifiable
    -0.42
    كون
    -0.42
    #![
    -0.41
     NSCoder
    -0.41
    CELONA
    -0.41
    POSITIVE LOGITS
     toc
    0.74
     doubtnut
    0.73
     houſe
    0.72
    scriptcase
    0.69
    MigrationBuilder
    0.68
     htons
    0.68
     Houſe
    0.66
    kháu
    0.66
    simpleType
    0.64
    getSeconds
    0.64
    Activations Density 0.136%

    No Known Activations