© 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
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 8022
    Prev
    Next
    INDEX
    Explanations

    references to raising or increasing awareness, concerns, or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DrawerToggle
    -0.46
     Einwilligung
    -0.43
     Erfindung
    -0.41
     Wahrheit
    -0.41
     Prensa
    -0.40
    orrhage
    -0.40
    onActivityResult
    -0.40
     referenties
    -0.38
    enza
    -0.38
    posób
    -0.37
    POSITIVE LOGITS
     eyebrows
    1.01
     awareness
    0.88
    awareness
    0.76
     eyebrow
    0.69
     expectations
    0.68
     consciousness
    0.67
     spirits
    0.66
     suspicions
    0.66
     flags
    0.64
    Awareness
    0.63
    Activations Density 0.189%

    No Known Activations