© 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. 38-GEMMASCOPE-RES-16K
    11. 14888
    Prev
    Next
    INDEX
    Explanations

    statistical values and references related to data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    それとも
    -0.47
    hoedd
    -0.36
    akei
    -0.34
    而已
    -0.34
    AddHtmlAttribute
    -0.33
    Autoritní
    -0.33
     createSlice
    -0.33
    vermögen
    -0.33
    gató
    -0.32
     snippetHide
    -0.32
    POSITIVE LOGITS
     especially
    4.63
     particularly
    4.09
    especially
    4.06
    Especially
    4.03
     Especially
    4.00
     especialmente
    3.75
    particularly
    3.66
     особенно
    3.53
     Particularly
    3.52
    特に
    3.27
    Activations Density 1.824%

    No Known Activations