© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-GEMMASCOPE-RES-16K
    11. 14215
    Prev
    Next
    INDEX
    Explanations

    HTML or JavaScript class names used for styling and element manipulation

    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
    er
    -0.88
    ers
    -0.62
    ergic
    -0.58
    erate
    -0.57
    culoskeletal
    -0.57
     a
    -0.56
    ER
    -0.55
     שוליים
    -0.55
    SizeF
    -0.55
    存于互联网档案馆
    -0.54
    POSITIVE LOGITS
    className
    0.56
     className
    0.54
    ClassName
    0.46
    ViewInit
    0.46
     endTime
    0.46
    chman
    0.43
    dington
    0.42
    FieldType
    0.41
    mode
    0.39
     principales
    0.39
    Activations Density 1.211%

    No Known Activations