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-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129927
    Prev
    Next
    INDEX
    Explanations

    terms and abbreviations related to XML and XSLT

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

    xs or xsl followed by : or =

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Slf
    -0.52
    ⓧ
    -0.52
    setCenter
    -0.45
     Pot
    -0.43
    inputValue
    -0.42
    Pot
    -0.41
    strophy
    -0.40
     Vladimir
    -0.40
     seme
    -0.40
    ed
    -0.39
    POSITIVE LOGITS
     XS
    0.66
    xs
    0.65
    XS
    0.61
     xs
    0.59
     mukana
    0.49
    Xs
    0.49
     Económica
    0.48
     Xs
    0.47
    sizeCache
    0.46
     asalto
    0.46
    Activations Density 0.001%

    No Known Activations