© 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. 4-GEMMASCOPE-RES-16K
    11. 2683
    Prev
    Next
    INDEX
    Explanations

    numerical data or values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dụ
    -0.49
    goku
    -0.47
    enei
    -0.45
     bi
    -0.45
    nesty
    -0.45
    ionine
    -0.44
    U
    -0.44
    стрі
    -0.43
    boten
    -0.43
     Para
    -0.41
    POSITIVE LOGITS
    ########.
    0.78
     незавершена
    0.77
    #+#
    0.76
     चीज़ों
    0.75
     wikipagina
    0.75
    MLLoader
    0.75
    ]--;
    0.74
     hefyd
    0.74
    jooq
    0.73
     Diſ
    0.73
    Activations Density 0.928%

    No Known Activations