© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 41-GEMMASCOPE-RES-16K
    11. 9524
    Prev
    Next
    INDEX
    Explanations

    references to quantity or frequency, particularly the word "many."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noen
    -0.56
     alguno
    -0.55
     some
    -0.54
    Certain
    -0.54
    some
    -0.54
     qualche
    -0.53
    certain
    -0.52
    ագրություններ
    -0.52
    ScopeManager
    -0.50
     några
    -0.50
    POSITIVE LOGITS
     different
    1.09
     thousands
    0.88
    different
    0.81
     facets
    0.79
    Different
    0.77
     verschiedene
    0.76
    不同的
    0.75
     verschiedenen
    0.72
     millions
    0.72
     hundreds
    0.71
    Activations Density 0.209%

    No Known Activations