© 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. 41-GEMMASCOPE-RES-16K
    11. 7386
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating user profile information and error messages related to profile settings

    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
     يتيمه
    -0.40
    ViewFeatures
    -0.39
    вић
    -0.38
    ptonshire
    -0.38
     yee
    -0.37
    gena
    -0.37
     виправивши
    -0.35
     ایک
    -0.35
     cref
    -0.35
    ihara
    -0.34
    POSITIVE LOGITS
     máis
    0.61
     tamén
    0.59
     unha
    0.58
     empreg
    0.51
     xa
    0.51
     moi
    0.49
     facendo
    0.48
     mell
    0.48
     veci
    0.46
     presenza
    0.46
    Activations Density 0.084%

    No Known Activations