© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8663
    Prev
    Next
    INDEX
    Explanations

    programming constructs that involve data structures and their manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shaksp
    -0.70
     LoggerFactory
    -0.69
     surla
    -0.68
    PDOException
    -0.62
     twilight
    -0.62
    Slf
    -0.62
     faſt
    -0.61
     smokes
    -0.60
     Shakspeare
    -0.60
     uſed
    -0.60
    POSITIVE LOGITS
     next
    0.71
    hasNext
    0.66
    next
    0.63
    setNext
    0.61
     فريبيس
    0.61
     NEXT
    0.60
    Next
    0.58
     Next
    0.57
     propOrder
    0.55
     Nachfolger
    0.54
    Activations Density 0.158%

    No Known Activations