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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106109
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "count" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     Glaser
    -0.53
    🏻
    -0.50
     оригіналу
    -0.47
     Dol
    -0.46
     Gerv
    -0.45
     Particular
    -0.44
    Particular
    -0.44
     Gav
    -0.44
     esclusivamente
    -0.44
     Fior
    -0.43
    POSITIVE LOGITS
    count
    1.16
     count
    1.13
    setCount
    1.12
    Count
    1.10
     Count
    1.04
     counts
    1.00
     Counts
    0.94
    COUNT
    0.94
     COUNT
    0.93
     totalCount
    0.90
    Activations Density 0.022%

    No Known Activations