© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 93820
    Prev
    Next
    INDEX
    Explanations

    the word "safely" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    safely + action word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     purpoſe
    -0.46
     thing
    -0.44
     certain
    -0.44
     przedmio
    -0.43
     eſt
    -0.42
     mijne
    -0.41
    เยอะ
    -0.40
     actualité
    -0.40
     things
    -0.40
     такі
    -0.40
    POSITIVE LOGITS
     safely
    1.96
     Safely
    1.80
    saf
    1.27
     securely
    1.20
    Saf
    1.07
     comfortably
    0.96
     reliably
    0.92
     profitably
    0.91
     confidently
    0.91
     successfully
    0.85
    Activations Density 0.003%

    No Known Activations