© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 63112
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to confidence intervals and predictive distributions in statistical modeling

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

    confidence intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    contentLoaded
    -0.56
    WithIOException
    -0.52
    SequentialGroup
    -0.49
    UnusedPrivate
    -0.49
     broek
    -0.48
    EndContext
    -0.46
    êmica
    -0.45
    SharedDtor
    -0.44
    Havolalar
    -0.44
     Überras
    -0.43
    POSITIVE LOGITS
     MainAxisSize
    0.47
     risk
    0.44
     probabilistic
    0.43
     uncertainty
    0.41
     risks
    0.41
     uncertainties
    0.37
    tableFuture
    0.36
     qual
    0.36
     confidence
    0.36
     statistical
    0.36
    Activations Density 0.100%

    No Known Activations