Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1802
    Prev
    Next
    INDEX
    Explanations

    elements related to structure and hierarchy within written content

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

    grammatical connective prepositions like "of", "as", "into", and "within".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    inclusion

    np_max-act-logits · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    execSQL
    -0.47
     sẻ
    -0.45
    っこう
    -0.44
    준
    -0.44
     dentelle
    -0.42
    ्रो
    -0.41
     ApiException
    -0.40
     đại
    -0.40
    en
    -0.40
     solides
    -0.40
    POSITIVE LOGITS
    mappedBy
    0.78
    ItemBackground
    0.77
    ContentAsync
    0.71
    amaño
    0.71
    脚注の使い方
    0.70
     فريبيس
    0.67
    tagext
    0.66
    ^(@)
    0.66
    (&$
    0.65
    WebServlet
    0.63
    Activations Density 0.445%

    No Known Activations