© 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. 33-GEMMASCOPE-RES-16K
    11. 8091
    Prev
    Next
    INDEX
    Explanations

    aspects related to organization and categorization in data-driven 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
    Xna
    -0.60
    GEBURTSDATUM
    -0.54
    RegressionTest
    -0.51
    exitRule
    -0.44
    expandindo
    -0.43
     désolés
    -0.43
     AspNetCore
    -0.42
     NSCoder
    -0.42
     ujednoznacz
    -0.41
    piecze
    -0.40
    POSITIVE LOGITS
     by
    2.16
     By
    1.45
    By
    1.41
    by
    1.22
     oleh
    1.11
    ByType
    1.10
     BY
    1.10
    ListBy
    1.04
    ById
    1.02
    ByName
    1.00
    Activations Density 1.205%

    No Known Activations