© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 39494
    Prev
    Next
    INDEX
    Explanations

    references to the classification or type of chemical compounds, specifically focusing on the designation of "Class III"

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

    Roman numeral III

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stination
    -0.69
     habet
    -0.63
    nthetic
    -0.62
    yntaxException
    -0.59
     scolas
    -0.58
     لات
    -0.57
    astify
    -0.57
    naby
    -0.56
    vestream
    -0.56
     Jop
    -0.55
    POSITIVE LOGITS
     III
    1.89
    III
    1.70
     iii
    1.38
    iii
    1.27
     Third
    1.04
    Ⅲ
    1.01
     third
    0.94
    Third
    0.93
     XIII
    0.90
     IV
    0.90
    Activations Density 0.010%

    No Known Activations