© 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. 12445
    Prev
    Next
    INDEX
    Explanations

    references to significant personal events, particularly those involving gifts and symbols of love, such as rings

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

    rings, ideals, and diamonds

    np_acts-logits-general · gemini-2.0-flash

    diamond and engagement rings

    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
    parsedMessage
    -0.68
    Bronze
    -0.56
     noqa
    -0.55
    bronze
    -0.55
    เหรียญ
    -0.54
    ViewFeatures
    -0.54
     Bronze
    -0.53
     COPPER
    -0.53
     समीक्षाएं
    -0.53
    xase
    -0.51
    POSITIVE LOGITS
    TagMode
    0.96
     engagement
    0.78
     solitaire
    0.74
     diamond
    0.72
     diamonds
    0.70
    GIA
    0.69
     marqu
    0.66
     Cushion
    0.66
    __*/
    0.65
     Engagement
    0.64
    Activations Density 0.146%

    No Known Activations