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. 14255
    Prev
    Next
    INDEX
    Explanations

    key financial or political terms related to electoral contributions and campaigns.

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

    information related to politics, elections, legislative processes, and legal cases.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words and phrases related to positions or roles within organizations, particularly focusing on seats, jobs, and official positions.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    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
     فريبيس
    -0.47
    ⅰ
    -0.47
    lichem
    -0.46
    bumptech
    -0.45
    sommer
    -0.45
    vault
    -0.44
     Spiritual
    -0.44
     Gusto
    -0.44
    rektor
    -0.44
    Insta
    -0.44
    POSITIVE LOGITS
     مرئيه
    0.65
     kosong
    0.64
    Geplaatst
    0.64
     vacated
    0.63
    verwijspagina
    0.63
    reszcie
    0.61
     availability
    0.60
     offered
    0.60
     resourceCulture
    0.59
    ագրություններ
    0.59
    Activations Density 0.229%

    No Known Activations