© 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. 19-GEMMASCOPE-RES-16K
    11. 15160
    Prev
    Next
    INDEX
    Explanations

    references to damage and deterioration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.72
    __*/
    -0.69
     betweenstory
    -0.64
    Sucesor
    -0.63
     exclusivity
    -0.62
    culin
    -0.61
    ConstraintMaker
    -0.61
    ViewFeatures
    -0.59
    存于互联网档案馆
    -0.58
    LayoutPanel
    -0.57
    POSITIVE LOGITS
     damaged
    1.35
     badly
    1.20
     broken
    1.14
     Damaged
    1.14
     severely
    1.08
    Damaged
    1.05
    damaged
    0.99
     rotten
    0.93
    broken
    0.92
     corrupted
    0.92
    Activations Density 0.496%

    No Known Activations