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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1812
    Prev
    Next
    INDEX
    Explanations

    references to specific authors and their works in academic contexts

    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
    Geplaatst
    -0.88
    abestanden
    -0.87
     ―――――
    -0.84
    kloped
    -0.82
    HtmlAttribute
    -0.82
    WindowConstants
    -0.81
    DeleteBehavior
    -0.81
    XmlAccessType
    -0.81
    Obrázky
    -0.80
    InSection
    -0.79
    POSITIVE LOGITS
     @
    0.73
    jning
    0.55
     venerable
    0.52
    @
    0.51
     
    0.50
     My
    0.50
    Zitat
    0.49
    في
    0.49
    poons
    0.48
    Moo
    0.48
    Activations Density 0.106%

    No Known Activations