© 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. 1085
    Prev
    Next
    INDEX
    Explanations

    elements related to forensic investigation and evidence

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

    Physical marks or traces

    np_acts-logits-general · gemini-2.0-flash

    leaving an imprint

    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
     للاسماء
    -0.68
    mobileqq
    -0.68
    BeginContext
    -0.65
    IsContent
    -0.65
    الحياه
    -0.65
     Administrativna
    -0.63
     vectorielles
    -0.63
    InstanceState
    -0.63
     propOrder
    -0.62
     nahilalakip
    -0.60
    POSITIVE LOGITS
     imprint
    1.51
     traces
    1.50
     mark
    1.49
     marks
    1.48
     footprints
    1.47
     footprint
    1.44
     Spuren
    1.34
     trace
    1.30
    mark
    1.22
    marks
    1.20
    Activations Density 0.384%

    No Known Activations