© 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. 3-GEMMASCOPE-RES-16K
    11. 8055
    Prev
    Next
    INDEX
    Explanations

    expressions of warnings or stern advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heça
    -0.61
    Cordialement
    -0.58
    Amicalement
    -0.57
    Bibliograf
    -0.57
    RenderAtEndOf
    -0.56
    SharedDtor
    -0.55
    новниш
    -0.52
    ništvo
    -0.51
    pozdrawiam
    -0.50
    ьаж
    -0.50
    POSITIVE LOGITS
     promised
    0.76
     warned
    0.74
    iastes
    0.73
     promise
    0.70
     promises
    0.65
    arschu
    0.64
     instructed
    0.61
     admon
    0.61
     StyleSheet
    0.61
     warnings
    0.60
    Activations Density 0.378%

    No Known Activations