© 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. 9278
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and the beginning of sentences

    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
    ↵↵
    -0.71
    ↵↵↵
    -0.57
    ↵↵↵↵
    -0.55
    <eos>
    -0.53
     ‘
    -0.51
    ↵
    -0.50
    ”
    -0.48
     or
    -0.48
    cy
    -0.47
    </strong>
    -0.46
    POSITIVE LOGITS
     Paglinawan
    0.95
    Diwedd
    0.93
     transfieras
    0.89
    AutoScaleMode
    0.85
    <bos>
    0.84
     allAfrica
    0.84
    IUrlHelper
    0.80
     purpoſe
    0.80
     chré
    0.77
     Савезне
    0.77
    Activations Density 0.346%

    No Known Activations