© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103362
    Prev
    Next
    INDEX
    Explanations

    credentials and certifications related to health and wellness professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.78
    principalTable
    -0.58
    Personendaten
    -0.58
    ьаж
    -0.52
    leſs
    -0.50
    ScopeManager
    -0.49
    ſelf
    -0.48
     HFILL
    -0.48
    IntoConstraints
    -0.47
    ſen
    -0.47
    POSITIVE LOGITS
     certification
    0.40
    Certified
    0.39
     certified
    0.39
     certify
    0.38
    enumerable
    0.38
     Certified
    0.37
     certificate
    0.36
     IFTT
    0.36
    posedge
    0.36
    ac
    0.35
    Activations Density 0.016%

    No Known Activations