© 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. 31-GEMMASCOPE-RES-16K
    11. 13258
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    full names of people, particularly first and last names together.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    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
    -0.41
    kungen
    -0.41
    !*\
    -0.39
    emlrt
    -0.38
    heme
    -0.37
     المعرف
    -0.36
     wet
    -0.35
     vux
    -0.34
    ilight
    -0.34
     treat
    -0.33
    POSITIVE LOGITS
    principalTable
    0.56
     informée
    0.51
     nonUne
    0.49
     John
    0.49
    John
    0.47
    tonode
    0.47
    errHandler
    0.46
    john
    0.45
     &[
    0.44
     joh
    0.44
    Activations Density 0.164%

    No Known Activations