© 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. 9-GEMMASCOPE-RES-16K
    11. 1039
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to various military and strategic contexts, including units and reconnaissance concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /***/
    -0.81
    łgorzata
    -0.80
    icoot
    -0.79
     StatelessWidget
    -0.76
     ModelExpression
    -0.75
    Économie
    -0.75
    ibatis
    -0.73
     estekak
    -0.73
    oughby
    -0.72
    Референце
    -0.72
    POSITIVE LOGITS
    nnnn
    1.41
    nnn
    1.25
    en
    1.16
    nen
    1.14
    nn
    1.10
    ning
    0.99
    hen
    0.99
    nin
    0.98
    han
    0.97
    ̀n
    0.95
    Activations Density 2.837%

    No Known Activations