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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11203
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bear" and its variations in different contexts

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

    "bear" (and its variations)

    np_acts-logits-general · gemini-2.0-flash

    bear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     للاسماء
    -0.59
    vinte
    -0.59
     grossa
    -0.58
     Dede
    -0.58
    jö
    -0.58
     manuale
    -0.57
    Kale
    -0.57
    thmus
    -0.57
    entary
    -0.56
    tymologie
    -0.55
    POSITIVE LOGITS
     bear
    1.56
     bears
    1.50
     Bear
    1.44
    Bear
    1.44
     Bears
    1.38
     BEAR
    1.38
    bear
    1.36
    BEAR
    1.26
    Bears
    1.24
    bears
    1.20
    Activations Density 0.086%

    No Known Activations