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. 2314
    Prev
    Next
    INDEX
    Explanations

    scientific terms and calculations related to physical properties and measurements.

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

    complex mathematical and scientific formulas and calculations.

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

    mathematical expressions with exponents, particularly those involving curly braces and superscript notation.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Mathematical or scientific expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation elements

    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
    msup
    -0.45
     am
    -0.44
    roben
    -0.43
     el
    -0.43
    ,
    -0.41
    ži
    -0.41
    êm
    -0.41
     pres
    -0.40
     tras
    -0.39
    ione
    -0.39
    POSITIVE LOGITS
    GEBURTSDATUM
    1.05
    IntoConstraints
    1.04
     متعلقه
    0.96
    Autoritní
    0.95
     autorytatywna
    0.94
     disambiguazione
    0.91
    Tikang
    0.87
     թվական
    0.87
    abestanden
    0.87
    enumi
    0.86
    Activations Density 0.743%

    No Known Activations