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. 10743
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific methods and evaluations

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

    preceding a preposition

    np_acts-logits-general · gemini-2.0-flash

    evidence or case

    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
    脚注の使い方
    -1.29
    تقاوى
    -1.28
    MigrationBuilder
    -1.21
     disambiguazione
    -1.13
    addCriterion
    -1.08
    Revenir
    -1.03
    SequentialGroup
    -1.02
     ExecuteAsync
    -1.01
     initComponents
    -0.99
     MainAxisSize
    -0.98
    POSITIVE LOGITS
    .
    0.69
     and
    0.67
    ,
    0.64
     (
    0.61
     is
    0.58
     &
    0.56
    /
    0.54
    ;
    0.53
     or
    0.53
    (
    0.52
    Activations Density 0.838%

    No Known Activations