© 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. 22-GEMMASCOPE-RES-16K
    11. 8993
    Prev
    Next
    INDEX
    Explanations

    instances of the word "see" and its variations

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

    "see" or a variation of it

    np_acts-logits-general · gemini-2.0-flash

    see or saw followed by observation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.68
     contextLoads
    -0.67
    انيف
    -0.65
     XNUMX
    -0.65
    bitat
    -0.58
    ArrowToggle
    -0.57
     Lokales
    -0.56
     Mainland
    -0.54
    ografija
    -0.54
     faptul
    -0.54
    POSITIVE LOGITS
     fit
    0.90
    Saw
    0.88
     sees
    0.81
    saw
    0.81
     how
    0.81
     clearly
    0.79
     eye
    0.78
     Sees
    0.76
    eye
    0.75
     وتسجيلات
    0.71
    Activations Density 0.116%

    No Known Activations