© 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. 8958
    Prev
    Next
    INDEX
    Explanations

    terms related to advertising, consumer behavior, and organizational dynamics

    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
     مرئيه
    -0.58
    tagHelperRunner
    -0.57
    новништво
    -0.41
    penup
    -0.37
     tắt
    -0.34
    Espèce
    -0.33
     équi
    -0.33
    kö
    -0.32
    XmlAccessType
    -0.32
     gug
    -0.31
    POSITIVE LOGITS
     rather
    0.65
     дописавши
    0.57
    Rather
    0.54
    rather
    0.53
     Italijanski
    0.52
     plutôt
    0.51
     Rather
    0.50
     Италијани
    0.50
    parsedMessage
    0.50
    elry
    0.49
    Activations Density 0.371%

    No Known Activations