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. 3-GEMMASCOPE-RES-16K
    6. 11153
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to code and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.58
    RenderAtEndOf
    -0.57
    ↵↵
    -0.55
     toscana
    -0.54
    WEBPACK
    -0.53
    winston
    -0.53
     الرخصة
    -0.53
    [toxicity=0]
    -0.50
     abstrait
    -0.50
    riedenheit
    -0.49
    POSITIVE LOGITS
    <bos>
    1.25
     Paglinawan
    0.83
    "),
    
    0.78
    ']")
    0.77
     disambiguazione
    0.75
     Administrativna
    0.74
    '),
    
    0.73
    :✨
    0.73
    IsContent
    0.71
     betweenstory
    0.70
    Activations Density 2.189%

    No Known Activations