© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11621
    Prev
    Next
    INDEX
    Explanations

    references to holding and accountability in various contexts

    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
    astify
    -0.56
    الحياه
    -0.56
     ***!
    -0.54
    CppMethod
    -0.52
     FAP
    -0.49
     Ames
    -0.47
    simpleType
    -0.45
    ToProps
    -0.45
    featureID
    -0.45
    randomUUID
    -0.45
    POSITIVE LOGITS
     hold
    2.08
     holding
    2.02
    Hold
    2.02
     Holding
    2.02
     Hold
    2.00
    Holding
    2.00
     holds
    1.96
     held
    1.94
    holding
    1.94
    hold
    1.92
    Activations Density 0.154%

    No Known Activations