© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9005
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "round" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avits
    -0.39
    છ
    -0.36
     pracow
    -0.35
    wirkt
    -0.35
     иму
    -0.35
     AppBar
    -0.33
     fakt
    -0.33
     servici
    -0.32
     génie
    -0.32
    RefreshLayout
    -0.32
    POSITIVE LOGITS
     round
    4.34
     Round
    3.95
    Round
    3.84
    round
    3.80
     ROUND
    3.67
    ROUND
    3.23
     rounds
    3.16
     Rounds
    2.94
    rounds
    2.72
    Rounds
    2.63
    Activations Density 0.070%

    No Known Activations