© 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. 23-GEMMASCOPE-RES-16K
    11. 8471
    Prev
    Next
    INDEX
    Explanations

    specific names and roles related to individuals and their associations, especially in contexts involving acknowledgment and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AxisAlignment
    -0.50
     Roskov
    -0.43
    الدراسه
    -0.42
    httphttps
    -0.41
    +#+#
    -0.41
    mergeFrom
    -0.41
    Vidite
    -0.41
    جستارهای
    -0.39
    سطس
    -0.39
     miliardi
    -0.39
    POSITIVE LOGITS
     noDo
    0.51
    Personensuche
    0.46
     Irán
    0.43
    ViewImports
    0.43
     unknownFields
    0.39
    Parcelize
    0.39
    Obrázky
    0.39
    RequestOptions
    0.38
    routeProvider
    0.37
     않는
    0.37
    Activations Density 1.346%

    No Known Activations