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. 10353
    Prev
    Next
    INDEX
    Explanations

    statistical analysis terms and related parameters

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

    Mathematical or chemical formulas/expressions

    np_acts-logits-general · gemini-2.0-flash

    equations with variables and comparisons

    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
     
    -0.86
     $\$
    -0.80
    Datuak
    -0.71
    脚注の使い方
    -0.71
    \%)
    -0.69
    曖昧さ回避
    -0.66
    \%,
    -0.66
    ^(@)
    -0.63
     chi̍t
    -0.63
    %</
    -0.62
    POSITIVE LOGITS
     scolaires
    0.66
     appartiennent
    0.63
     présidenti
    0.62
     démocr
    0.61
     indépendante
    0.60
     Etats
    0.58
     Donde
    0.58
     obligatoire
    0.57
     =
    0.57
     dimana
    0.57
    Activations Density 4.848%

    No Known Activations