© 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. 3-GEMMASCOPE-RES-16K
    11. 3192
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])->
    -0.53
    ...»
    -0.52
    featureID
    -0.50
    /...
    -0.50
    ...)
    -0.50
     ...
    -0.49
    hassee
    -0.49
    DoubleQuotes
    -0.48
     ...)
    -0.48
    +:+
    -0.48
    POSITIVE LOGITS
    「
    1.01
    【
    0.94
    『
    0.92
    《
    0.91
     Efq
    0.89
     leaſt
    0.86
    ISupport
    0.85
    ｢
    0.82
     quæ
    0.79
     houſe
    0.78
    Activations Density 0.405%

    No Known Activations