© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 6212
    Prev
    Next
    INDEX
    Explanations

    mathematical and logical constructs related to definitions and properties of objects, particularly in the context of advanced topics like limits and topology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.86
    esModule
    -0.63
    twimg
    -0.62
    Ane
    -0.62
    Eti
    -0.61
    Evid
    -0.60
    Ante
    -0.56
    Avan
    -0.55
    Aux
    -0.54
    providedIn
    -0.54
    POSITIVE LOGITS
     an
    1.61
     nouvel
    0.83
    épaisseur
    0.73
    extrémité
    0.71
    empêcher
    0.71
    amitié
    0.70
    événement
    0.65
    entraînement
    0.64
    humanité
    0.63
    équipement
    0.63
    Activations Density 0.747%

    No Known Activations