© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15785
    Prev
    Next
    INDEX
    Explanations

    references to multiple components or groups within a context

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

    lists or enumerations divided into multiple categories or classifications.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     birçok
    -0.72
     wielu
    -0.71
     berbagai
    -0.70
     pelbagai
    -0.65
     многих
    -0.65
     vieler
    -0.63
     רבים
    -0.61
     många
    -0.59
     zahlreichen
    -0.59
     várias
    -0.58
    POSITIVE LOGITS
     namely
    1.34
    分别是
    1.13
    namely
    1.13
    分別
    1.01
     Namely
    0.94
     viz
    0.88
     namelijk
    0.86
    分别
    0.82
     nemlig
    0.82
     nämlich
    0.82
    Activations Density 0.799%

    No Known Activations