© 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. 14441
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to safety systems and assessments

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

    safety analysis and data

    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
    BagConstraints
    -0.59
     ModelExpression
    -0.54
     mijne
    -0.54
    Tikang
    -0.49
    etCode
    -0.48
    makeConstraints
    -0.45
    writerow
    -0.45
    Javadoc
    -0.44
    TableAdapter
    -0.44
     verdieping
    -0.43
    POSITIVE LOGITS
    Safety
    1.65
     safety
    1.59
     Safety
    1.56
    safety
    1.53
     SAFETY
    1.41
    SAFETY
    1.35
    afety
    1.20
     Sicherheits
    1.16
    安全
    1.06
     sécurité
    1.05
    Activations Density 0.011%

    No Known Activations