© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 37192
    Prev
    Next
    INDEX
    Explanations

    instances of the words "upside" and "down" in various contexts

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

    ups and downs

    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
    bibfield
    -0.65
     føl
    -0.56
    bibinfo
    -0.54
     aleación
    -0.52
     cejas
    -0.48
     novedades
    -0.48
     testigo
    -0.47
     prestaciones
    -0.47
     perlas
    -0.47
     nabí
    -0.47
    POSITIVE LOGITS
     upside
    0.85
     Upside
    0.78
     inverted
    0.63
    underwater
    0.56
     crooked
    0.54
     invis
    0.53
     vertical
    0.52
     invisible
    0.51
     underwater
    0.49
    inverted
    0.49
    Activations Density 0.003%

    No Known Activations