© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 81323
    Prev
    Next
    INDEX
    Explanations

    specific mineral types, particularly those containing "ite."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    words ending in ite

    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
    Negative Logits
     AssemblyCompany
    -0.57
     }}"></
    -0.56
     overla
    -0.54
     تضيفلها
    -0.54
    lapsingToolbar
    -0.53
    ::_('
    -0.50
    Jeografia
    -0.50
    ьажоргаш
    -0.49
     olymp
    -0.48
     informée
    -0.48
    POSITIVE LOGITS
    ite
    2.89
    ITE
    2.17
    ites
    1.85
    ITES
    1.48
    îte
    1.20
     ite
    1.19
    nite
    1.16
    dite
    1.15
    tite
    1.13
    lite
    1.12
    Activations Density 0.008%

    No Known Activations