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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2464
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to insurance policies and their conditions

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

    after place names or organizations

    np_acts-logits-general · gemini-2.0-flash

    company names and cities

    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
     vectorielles
    -0.69
     confronti
    -0.68
     nakalista
    -0.68
     traditionnelle
    -0.66
     polaire
    -0.65
     traditionnels
    -0.65
     mukana
    -0.65
     vostri
    -0.62
     fondament
    -0.61
     nucléaire
    -0.61
    POSITIVE LOGITS
    IsMutable
    0.67
    RenderAtEndOf
    0.54
    brida
    0.52
    westen
    0.49
    moud
    0.48
    SuppressMessage
    0.47
     defaultstate
    0.46
    جغرافيا
    0.46
    autoconfigure
    0.46
    BuildContext
    0.46
    Activations Density 0.186%

    No Known Activations