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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 7443
    Prev
    Next
    INDEX
    Explanations

    references to accidents or catastrophic events, particularly those related to wrecks and horror themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maketitle
    -0.62
    taban
    -0.59
    KEYCODE
    -0.57
    InSection
    -0.54
    GIVEREF
    -0.54
    存于互联网档案馆
    -0.52
    stretchr
    -0.52
    jata
    -0.51
    eseorang
    -0.51
     nahilalakip
    -0.50
    POSITIVE LOGITS
     wreck
    1.23
     wrecks
    1.12
     Wreck
    0.99
     Wre
    0.88
     wrecked
    0.87
     horror
    0.86
    horror
    0.86
    wreck
    0.85
     wre
    0.81
     wreckage
    0.79
    Activations Density 0.019%

    No Known Activations