© 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. 20-GEMMASCOPE-RES-16K
    11. 16106
    Prev
    Next
    INDEX
    Explanations

    terms related to physical damage or deterioration

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

    Describes something broken, damaged, or detached

    np_acts-logits-general · gemini-2.0-flash

    physical states of damage or wear

    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
    /*
    -0.74
    AddHtmlAttribute
    -0.63
     implicitly
    -0.59
     للمعارف
    -0.58
    kháu
    -0.56
    HasAnnotation
    -0.55
    енча
    -0.54
    campal
    -0.52
    nteral
    -0.52
    TagMode
    -0.52
    POSITIVE LOGITS
     underneath
    0.56
     Caused
    0.56
     ressemb
    0.55
     pieces
    0.55
     caused
    0.54
     resembling
    0.54
     chunks
    0.54
     lodged
    0.53
     plastica
    0.53
     clinging
    0.52
    Activations Density 0.432%

    No Known Activations