© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 28313
    Prev
    Next
    INDEX
    Explanations

    references to the term "bear" in various contexts

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

    bear and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mx
    -0.59
     McCormack
    -0.58
     mex
    -0.55
    onix
    -0.55
    tils
    -0.55
     arşivlendi
    -0.52
    Mx
    -0.52
    Deco
    -0.52
     Luci
    -0.51
     Choco
    -0.51
    POSITIVE LOGITS
     bear
    2.08
     Bear
    2.06
    Bear
    1.98
    bear
    1.93
     BEAR
    1.80
     bears
    1.71
    BEAR
    1.63
     Bears
    1.48
    bears
    1.46
     bearing
    1.38
    Activations Density 0.006%

    No Known Activations