© 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. 13-GEMMASCOPE-RES-16K
    11. 14078
    Prev
    Next
    INDEX
    Explanations

    phrases describing actions involving motion or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.57
     nahilalakip
    -0.57
    clusal
    -0.53
    ||}
    -0.47
    Източници
    -0.47
     Wohl
    -0.46
    kuuta
    -0.46
    tava
    -0.46
    Chham
    -0.45
    worked
    -0.45
    POSITIVE LOGITS
     walking
    1.04
     walk
    0.95
     walks
    0.93
     walked
    0.87
     walkways
    0.86
     walkway
    0.84
    🚶
    0.84
     Walks
    0.83
    walking
    0.82
     strolling
    0.81
    Activations Density 0.357%

    No Known Activations