© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 206
    Prev
    Next
    INDEX
    Explanations

    action words related to legal and political demands or requests

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

    "demands" or "requesting" something

    np_acts-logits-general · gemini-2.0-flash

    demanding to stop or end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.98
    StoryboardSegue
    -0.89
    +#+#
    -0.88
     فريبيس
    -0.79
    تقاوى
    -0.79
    sizeCache
    -0.73
    évaluateur
    -0.73
    abestanden
    -0.72
    posedge
    -0.72
     Roskov
    -0.71
    POSITIVE LOGITS
     halt
    0.77
     immediate
    0.73
     cesse
    0.71
     stop
    0.69
     abolish
    0.65
     reinstate
    0.63
     immédi
    0.61
     ban
    0.61
     endlich
    0.60
     end
    0.60
    Activations Density 0.421%

    No Known Activations