© 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. 24-GEMMASCOPE-RES-16K
    11. 14611
    Prev
    Next
    INDEX
    Explanations

    references to care in various contexts, highlighting the importance of caregiving and consideration in situations described

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

    "care" and words following it

    np_acts-logits-general · gemini-2.0-flash

    care delivery and taking care

    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
    InstrumentedTest
    -0.78
    الحياه
    -0.78
    RenderAtEndOf
    -0.77
    BeginContext
    -0.75
    اریخ
    -0.70
     فريبيس
    -0.68
     lenker
    -0.66
    IsMutable
    -0.66
    enderror
    -0.66
    principalColumn
    -0.65
    POSITIVE LOGITS
    takers
    0.85
    giving
    0.82
    ssing
    0.77
    taking
    0.74
    taker
    0.71
    sses
    0.68
     taker
    0.58
     giver
    0.58
    giver
    0.57
     gi
    0.55
    Activations Density 0.094%

    No Known Activations