© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15859
    Prev
    Next
    INDEX
    Explanations

    references to blood, violence, and bodily harm

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

    Following "of," "in," or "with."

    np_acts-logits-general · gemini-2.0-flash

    substances and materials

    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
    GraphicsUnit
    -0.56
    PhysRevLett
    -0.52
     OkHttpClient
    -0.51
    gatsby
    -0.49
     një
    -0.48
     portée
    -0.48
    ึกษา
    -0.48
     accompan
    -0.47
     antenn
    -0.47
     voeten
    -0.47
    POSITIVE LOGITS
     dust
    0.85
     grease
    0.84
     dirt
    0.82
     smoke
    0.80
     sand
    0.78
     mud
    0.77
     sawdust
    0.73
     snow
    0.71
     blood
    0.70
     grime
    0.70
    Activations Density 0.458%

    No Known Activations