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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13996
    Prev
    Next
    INDEX
    Explanations

    terms related to animal behavior and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.50
    handa
    -0.49
     Hand
    -0.45
    bable
    -0.45
     рукой
    -0.45
    SqlClient
    -0.44
    setCharacter
    -0.43
     Hands
    -0.43
     насељу
    -0.43
    zburg
    -0.42
    POSITIVE LOGITS
     foraging
    0.93
     sniffing
    0.92
     gna
    0.90
     nib
    0.87
     munch
    0.86
     feasting
    0.84
     licking
    0.83
     eating
    0.82
     roaming
    0.79
     chewing
    0.77
    Activations Density 0.285%

    No Known Activations