© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4903
    Prev
    Next
    INDEX
    Explanations

    mentions and references to programming extensions or modules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.86
     صوتيه
    -0.86
    Geplaatst
    -0.85
     للمعارف
    -0.80
     suprême
    -0.79
    脚注の使い方
    -0.78
    PreExecute
    -0.76
    PMailer
    -0.76
     récon
    -0.75
     peindre
    -0.75
    POSITIVE LOGITS
     extension
    3.90
     Extension
    3.63
    Extension
    3.53
    extension
    3.49
     extensions
    3.38
     EXTENSION
    3.11
     Extensions
    2.96
    EXTENSION
    2.84
    extensions
    2.77
    Extensions
    2.52
    Activations Density 0.089%

    No Known Activations