© 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. 8256
    Prev
    Next
    INDEX
    Explanations

    processes and methodologies in technical or scientific contexts

    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
    tagHelperRunner
    -0.75
    bootstrapcdn
    -0.70
    httphttps
    -0.69
     Савезне
    -0.68
     Италијани
    -0.67
     tartalomajánló
    -0.66
    transQ
    -0.66
     betweenstory
    -0.65
    parsedMessage
    -0.64
     BrowserModule
    -0.62
    POSITIVE LOGITS
     the
    0.52
     principal
    0.40
    Car
    0.40
     tanah
    0.39
     Hols
    0.39
    a
    0.38
     apprécié
    0.38
    ooker
    0.38
    ba
    0.37
     Car
    0.37
    Activations Density 0.726%

    No Known Activations