© 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. 13-GEMMASCOPE-RES-65K
    11. 2956
    Prev
    Next
    INDEX
    Explanations

    terms related to hazards and risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -1.03
    opsida
    -0.90
    DotNetBar
    -0.84
     argv
    -0.77
    й
    -0.76
     monocytes
    -0.73
    itettura
    -0.73
    IndentedString
    -0.73
     Conroy
    -0.72
    ynb
    -0.72
    POSITIVE LOGITS
     hazard
    1.41
     hazards
    1.40
     Hazard
    1.34
     Hazards
    1.30
    hazard
    1.28
    Hazard
    1.13
    Hazards
    1.13
     HAZARD
    0.99
     hazardous
    0.97
    hazardous
    0.97
    Activations Density 0.010%

    No Known Activations