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. 16-GEMMASCOPE-RES-16K
    6. 12658
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to sports and competitions

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

    Numbers followed by context

    np_acts-logits-general · gemini-2.0-flash

    years, numbers, and song titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EnglishChoose
    -0.65
     ویکی‌پدیا
    -0.59
    تقاوى
    -0.56
     voud
    -0.55
    Enllaços
    -0.55
    liess
    -0.53
    \",\"
    -0.52
     highly
    -0.52
     the
    -0.52
    erapa
    -0.52
    POSITIVE LOGITS
    ⓘ
    0.74
    </td>
    0.73
    <sup>
    0.68
    featureID
    0.59
    󠁿
    0.58
     disambiguazione
    0.58
     withdrew
    0.57
    [?]
    0.56
    EDEFAULT
    0.56
     initComponents
    0.55
    Activations Density 0.221%

    No Known Activations