© 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. 6240
    Prev
    Next
    INDEX
    Explanations

    references to media, characters, or cultural aspects related to minority representation and experiences

    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
    
    -0.66
    WebElementEntity
    -0.64
     IBOutlet
    -0.63
     transfieras
    -0.63
     AssemblyCulture
    -0.59
    #+#
    -0.56
     Audiodateien
    -0.56
    +#+
    -0.55
    ſchaft
    -0.55
    thâu
    -0.54
    POSITIVE LOGITS
     irmã
    0.33
     devriez
    0.32
    道
    0.30
    ByVersion
    0.30
     von
    0.30
     Neither
    0.29
     others
    0.29
     
    0.29
    weightedMode
    0.28
     jeder
    0.28
    Activations Density 0.388%

    No Known Activations