© 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. 39-GEMMASCOPE-RES-16K
    11. 2248
    Prev
    Next
    INDEX
    Explanations

    keywords related to searching and retrieving information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hikariConfig
    -0.38
     Stufe
    -0.35
    shed
    -0.35
    мят
    -0.35
    Shady
    -0.34
    }{*}{}
    -0.34
    glVertex
    -0.33
    énario
    -0.33
     Stufen
    -0.33
    estinos
    -0.32
    POSITIVE LOGITS
     search
    3.77
     Search
    3.25
    search
    3.20
     SEARCH
    3.05
    Search
    3.05
     searches
    3.05
     searched
    2.91
    SEARCH
    2.80
     searching
    2.72
    搜索
    2.66
    Activations Density 1.315%

    No Known Activations