© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9161
    Prev
    Next
    INDEX
    Explanations

    references to racial disparities in justifiable homicide cases

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

    Numbers followed by "percent" or "per cent"

    np_acts-logits-general · gemini-2.0-flash

    percentages and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gdx
    -0.60
    SequentialGroup
    -0.59
    jsonwebtoken
    -0.57
     calendriers
    -0.56
    vindo
    -0.56
     Cualquier
    -0.56
     vroeger
    -0.56
     gärna
    -0.54
     wszel
    -0.54
     anything
    -0.53
    POSITIVE LOGITS
    Only
    1.10
     Nearly
    1.09
     Seventy
    1.09
     Eighty
    1.08
     Only
    1.08
    Nearly
    1.07
     Among
    1.06
     Ninety
    1.05
     Sixty
    1.05
     Forty
    1.03
    Activations Density 0.747%

    No Known Activations