© 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. 4023
    Prev
    Next
    INDEX
    Explanations

    mentions of academic subjects and disciplines, particularly in the social sciences, healthcare, and STEM fields

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

    academic disciplines and departments like "Arts & Sciences," "Faculty of Medicine," or "Social Sciences."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    academic and institutional affiliations, particularly departmental and faculty listings.

    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
    webElementXpaths
    -0.42
     uitge
    -0.40
     CreateTagHelper
    -0.40
     StatelessWidget
    -0.38
     fö
    -0.38
    borderFill
    -0.38
     etched
    -0.36
    quese
    -0.36
    FlatAppearance
    -0.36
    forgettable
    -0.35
    POSITIVE LOGITS
     arts
    1.52
     sciences
    1.39
     Arts
    1.23
    sciences
    1.20
    arts
    1.19
    Arts
    1.15
     Sciences
    1.12
     humanities
    1.11
     science
    1.05
     ARTS
    1.04
    Activations Density 0.168%

    No Known Activations