© 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. 14553
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to individuals and their attributes

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

    descriptive passages about people's physical appearance and detailed scene settings.

    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
    awsze
    -0.38
    siempre
    -0.37
     zawsze
    -0.34
    lepší
    -0.34
     czasem
    -0.33
     siempre
    -0.33
    每天
    -0.33
     gelieb
    -0.33
     """",
    -0.32
    lwjgl
    -0.32
    POSITIVE LOGITS
     seemingly
    0.90
     apparently
    0.88
     offensichtlich
    0.86
     للاسماء
    0.84
     apparent
    0.84
    presumably
    0.83
    apparently
    0.83
     seeming
    0.81
     evidently
    0.80
     presumably
    0.79
    Activations Density 0.457%

    No Known Activations