© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 99
    Prev
    Next
    INDEX
    Explanations

    code structure attributes such as class definitions and method declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Izvori
    -0.54
    sendRedirect
    -0.48
    coher
    -0.47
     nakalista
    -0.44
    ven
    -0.43
    渡
    -0.43
    ñan
    -0.43
    expandindo
    -0.43
    nonatomic
    -0.42
     brengen
    -0.42
    POSITIVE LOGITS
     this
    0.78
    this
    0.68
    WithFormat
    0.65
     ésta
    0.57
    RegressionTest
    0.56
     تانيه
    0.55
    ylation
    0.55
    chitz
    0.54
    ptonshire
    0.54
    gestone
    0.53
    Activations Density 0.014%

    No Known Activations