© 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. 12975
    Prev
    Next
    INDEX
    Explanations

    terms related to color, fibers, and their characteristics in scientific contexts

    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
     enggak
    -1.60
     creș
    -1.46
     ști
    -1.34
     ๆ
    -1.33
     maș
    -1.30
     uș
    -1.30
    anță
    -1.23
     și
    -1.21
    Și
    -1.20
     viață
    -1.20
    POSITIVE LOGITS
     sólo
    1.72
     grossen
    1.67
     gröss
    1.62
     äusser
    1.56
     colour
    1.55
    Sólo
    1.55
     tumour
    1.53
     şi
    1.53
     ausser
    1.53
     neighbourhood
    1.51
    Activations Density 0.784%

    No Known Activations