© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 110734
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to statistical underreporting and estimation

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

    estimate and underestimate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nought
    -0.49
    گاب
    -0.46
    fromCharCode
    -0.39
     aapt
    -0.36
    ImageContext
    -0.35
    \{\\
    -0.35
    Spe
    -0.35
     lenker
    -0.34
    รก
    -0.34
    anteed
    -0.34
    POSITIVE LOGITS
     estimates
    1.02
     estimate
    0.91
     estimations
    0.90
     underestimated
    0.85
     Estimates
    0.85
     underestimate
    0.82
     estimating
    0.82
     estimated
    0.82
     undetected
    0.81
     estimation
    0.80
    Activations Density 0.096%

    No Known Activations