© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4492
    Prev
    Next
    INDEX
    Explanations

    references to the prefix "co-" indicating cooperative or joint activities

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

    "Co" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    co- prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    риях
    -0.31
     jueves
    -0.30
    ibatis
    -0.30
     hinweg
    -0.29
     uș
    -0.29
    houette
    -0.29
     Marcell
    -0.29
     Signalez
    -0.29
     tent
    -0.28
     Näch
    -0.28
    POSITIVE LOGITS
     Co
    0.73
     co
    0.69
    HideFlags
    0.68
    Co
    0.68
    expandindo
    0.66
     Cof
    0.63
    Попис
    0.63
     cof
    0.60
    CoA
    0.58
     تكبرها
    0.57
    Activations Density 0.311%

    No Known Activations