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. 1810
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    SourceChecksum
    -1.20
     tartalomajánló
    -1.07
    queryInterface
    -1.05
    StoryboardSegue
    -1.01
    ViewImports
    -0.96
    invokeLater
    -0.94
    AndEndTag
    -0.89
    ädie
    -0.89
    principalTable
    -0.89
    hasMoreElements
    -0.89
    POSITIVE LOGITS
    Drawing
    0.53
     Balo
    0.52
     drawings
    0.47
     Dibu
    0.47
     dibu
    0.46
     BoxDecoration
    0.45
     Drawings
    0.44
    drawable
    0.43
     Jungen
    0.43
     Rubens
    0.43
    Activations Density 0.002%

    No Known Activations