© 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. 1-GEMMASCOPE-RES-16K
    11. 2588
    Prev
    Next
    INDEX
    Explanations

    references to products or services related to technology or health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.79
     للاسماء
    -0.71
    RenderAtEndOf
    -0.69
    ///</
    -0.64
    GTCX
    -0.57
    liferay
    -0.57
     ligiloj
    -0.53
    RTLR
    -0.52
    GOTREF
    -0.51
    VIAF
    -0.51
    POSITIVE LOGITS
    ível
    0.35
     Pembangunan
    0.35
    Ѕ
    0.35
     ſame
    0.34
    entlicher
    0.34
     Geschenk
    0.33
     solicitudes
    0.33
     Autobahn
    0.33
     feil
    0.33
    tschafts
    0.33
    Activations Density 0.397%

    No Known Activations