© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 22733
    Prev
    Next
    INDEX
    Explanations

    phrases indicating gaps or underutilization in treatment for alcohol use disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.70
     uſed
    -0.66
     chofe
    -0.65
    ">//
    -0.62
     himſelf
    -0.59
    +#+#
    -0.59
     alſo
    -0.57
     raiſ
    -0.56
     Efq
    -0.56
     faſt
    -0.55
    POSITIVE LOGITS
     lack
    0.67
     manque
    0.63
     Lack
    0.62
     insuffisamment
    0.60
    Lack
    0.58
     spesso
    0.58
     inadequate
    0.57
     lacking
    0.57
     Pourtant
    0.55
     manquer
    0.55
    Activations Density 0.087%

    No Known Activations