© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7675
    Prev
    Next
    INDEX
    Explanations

    references to parties involved in legal agreements or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.74
     disambiguazione
    -0.68
     ddelweddau
    -0.68
    SharedCtor
    -0.67
     colectiva
    -0.65
     thơ
    -0.65
     Normdatei
    -0.64
     للاسماء
    -0.64
     Kebijakan
    -0.64
     للمعارف
    -0.62
    POSITIVE LOGITS
     teams
    1.39
     groups
    1.29
    Teams
    1.14
     sides
    1.11
     Teams
    1.09
     parties
    1.04
    teams
    1.01
    groups
    1.00
     Groups
    0.99
    Groups
    0.91
    Activations Density 0.195%

    No Known Activations