Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 6234
    Prev
    Next
    INDEX
    Explanations

    references to "bear" in various contexts, including physical burdens, animals, and metaphorical uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.77
    adaptiveStyles
    -0.77
     Neust
    -0.76
    ciutto
    -0.76
    aculture
    -0.75
    losigkeit
    -0.75
     errand
    -0.71
     Bakker
    -0.71
     versa
    -0.71
     Araujo
    -0.70
    POSITIVE LOGITS
     bear
    2.24
     bears
    2.23
    bear
    2.11
     Bear
    2.09
     Bears
    2.08
     BEAR
    2.08
    Bear
    2.07
    Bears
    1.80
    BEAR
    1.76
    bears
    1.70
    Activations Density 0.061%

    No Known Activations