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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 2261
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to chemical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Brother
    -0.48
    awtextra
    -0.45
     Brother
    -0.45
     Eighteen
    -0.44
     hermano
    -0.44
     gatto
    -0.44
     brother
    -0.43
     Fourteen
    -0.43
    useEffect
    -0.42
    umumkan
    -0.41
    POSITIVE LOGITS
    5
    1.55
     fifth
    1.39
     Fifth
    1.32
     five
    1.30
     FIVE
    1.26
    Fifth
    1.21
     FIFTH
    1.18
     Five
    1.18
    5
    1.15
     cinque
    1.14
    Activations Density 1.218%

    No Known Activations