© 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. 22-GEMMASCOPE-RES-16K
    11. 9264
    Prev
    Next
    INDEX
    Explanations

    names and references to relationships among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ronpa
    -0.34
    Espèce
    -0.33
     Micro
    -0.30
     micro
    -0.29
     Re
    -0.28
     Try
    -0.28
    Autoritní
    -0.27
    реди
    -0.26
    adaptiveStyles
    -0.26
     le
    -0.26
    POSITIVE LOGITS
    Parcelize
    0.75
    XmlAccessorType
    0.75
    featureID
    0.74
    ThroughAttribute
    0.73
    boss
    0.62
    Boss
    0.61
    pecabe
    0.60
     MainAxisSize
    0.60
     CURIAM
    0.59
    ciller
    0.58
    Activations Density 0.585%

    No Known Activations