© 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. 16-GEMMASCOPE-RES-16K
    11. 7896
    Prev
    Next
    INDEX
    Explanations

    the word "Notice" and variations related to noting or acknowledging something

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

    Text after the word "Notice"

    np_acts-logits-general · gemini-2.0-flash

    introducing specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Celeste
    -0.77
     NDC
    -0.73
    Celeste
    -0.70
    jstor
    -0.69
     lentes
    -0.68
     McCullough
    -0.67
     Aquila
    -0.66
    calyp
    -0.66
    ništvo
    -0.65
    MediaStore
    -0.64
    POSITIVE LOGITS
    ##
    0.86
    ]]
    0.83
     glab
    0.82
     Linus
    0.80
     NUKAT
    0.78
     Daf
    0.78
    jspx
    0.77
    ureka
    0.76
    getSystemService
    0.76
    ."</
    0.76
    Activations Density 0.631%

    No Known Activations