© 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. 9-GEMMASCOPE-RES-16K
    11. 7760
    Prev
    Next
    INDEX
    Explanations

    references to alerts and notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Use
    -0.40
     endIndex
    -0.40
    use
    -0.39
     közé
    -0.39
    GOTREF
    -0.36
     dyr
    -0.34
    entretien
    -0.32
     Ausland
    -0.32
     bedrijf
    -0.31
     européennes
    -0.31
    POSITIVE LOGITS
     alert
    2.23
    alert
    2.19
     Alert
    2.13
    Alert
    1.99
     alerts
    1.92
     ALERT
    1.86
     Alerts
    1.79
    alerts
    1.72
    Alerts
    1.70
     alerting
    1.66
    Activations Density 0.076%

    No Known Activations