© 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. 16-GEMMASCOPE-RES-16K
    11. 4532
    Prev
    Next
    INDEX
    Explanations

    references to stains or contaminants, particularly related to substances like blood or ink

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

    Spills, smearing, and stains

    np_acts-logits-general · gemini-2.0-flash

    blood stains and spills

    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
    AutoField
    -0.55
     FormGroup
    -0.53
     enslaved
    -0.52
    šana
    -0.51
     flutes
    -0.49
     financiar
    -0.49
     flute
    -0.49
     neuropathy
    -0.49
     voice
    -0.48
    AlterField
    -0.48
    POSITIVE LOGITS
     stains
    0.85
     spilled
    0.77
     stain
    0.77
    脚注の使い方
    0.77
     spill
    0.69
     spray
    0.69
     spilt
    0.69
     staining
    0.67
    InitVars
    0.66
     splat
    0.65
    Activations Density 0.282%

    No Known Activations