© 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 - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15467
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or procedures that involve taking steps or measures for safety and prevention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gql
    -0.55
    argout
    -0.53
    RuleContext
    -0.53
    Xna
    -0.52
     предъ
    -0.51
     livré
    -0.50
    lieferung
    -0.50
    NewUrlParser
    -0.48
    ndice
    -0.48
     orgasm
    -0.47
    POSITIVE LOGITS
     measures
    1.42
     steps
    1.41
     Measures
    1.24
     Steps
    1.24
     mesures
    1.22
    Measures
    1.22
     precautions
    1.20
    measures
    1.20
    steps
    1.20
     MEASURES
    1.15
    Activations Density 0.197%

    No Known Activations