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

    Neuronpedia

    Jacobian LensNEW
    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. 14727
    Prev
    Next
    INDEX
    Explanations

    dates, events, and specific occurrences

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

    preceding dates or times

    np_acts-logits-general · gemini-2.0-flash

    dates and times

    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
     åren
    -0.47
    Vaya
    -0.41
    CopyWith
    -0.41
    featureID
    -0.41
     året
    -0.40
    PRWEB
    -0.40
    styleable
    -0.40
    bitkan
    -0.40
     hatır
    -0.40
     برانيه
    -0.39
    POSITIVE LOGITS
     tomorrow
    0.77
    tomorrow
    0.70
    HasColumnName
    0.67
    GetKeyDown
    0.66
     tonight
    0.62
     MonoBehaviour
    0.62
    cokinetic
    0.61
    UnknownFields
    0.60
    ."));
    0.59
     Tonight
    0.58
    Activations Density 0.093%

    No Known Activations