© 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. 20-GEMMASCOPE-RES-16K
    11. 90
    Prev
    Next
    INDEX
    Explanations

    statistical data related to confidence intervals and hazard ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Confidence intervals

    np_acts-logits-general · gemini-2.0-flash

    confidence interval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.74
    PerformLayout
    -0.61
    AutoScaleMode
    -0.59
     оригіналу
    -0.56
    tonsoft
    -0.54
    hassee
    -0.54
    InSection
    -0.54
    exitRule
    -0.53
     useDispatch
    -0.51
    Coordonnées
    -0.50
    POSITIVE LOGITS
     confidence
    1.05
     Confidence
    0.91
    confidence
    0.85
    Confidence
    0.84
     confident
    0.75
    CI
    0.71
     confianza
    0.71
     kepercayaan
    0.71
     interval
    0.70
     CI
    0.69
    Activations Density 0.620%

    No Known Activations