© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 115717
    Prev
    Next
    INDEX
    Explanations

    references to safety and secure environments

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

    safe places, ways, and planning

    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
    Not in Any Lists

    No Comments

    Negative Logits
     QtWidgets
    -0.52
     ujednoznacz
    -0.49
    JsonHelper
    -0.48
    DialogComponent
    -0.47
    rétaire
    -0.47
     Einfluß
    -0.45
    หน้านี้
    -0.45
    toCharArray
    -0.44
    iastes
    -0.43
    hexa
    -0.43
    POSITIVE LOGITS
     safe
    1.00
    safe
    0.96
     safest
    0.94
     Safe
    0.93
    Safe
    0.87
     safer
    0.85
     safety
    0.81
    safety
    0.80
     bezpiecz
    0.77
    SAFE
    0.76
    Activations Density 0.014%

    No Known Activations