© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11640
    Prev
    Next
    INDEX
    Explanations

    parentheses and related punctuation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -1.07
    AndEndTag
    -1.01
    featureID
    -0.96
    IntoConstraints
    -0.92
    ngdoc
    -0.87
     وتسجيلات
    -0.86
     незавершена
    -0.85
    {}",
    -0.85
    ImageContext
    -0.84
    fromnode
    -0.83
    POSITIVE LOGITS
    .(
    0.57
     (
    0.57
    p
    0.56
    j
    0.54
    c
    0.53
    A
    0.51
    By
    0.50
    v
    0.50
    f
    0.48
    C
    0.48
    Activations Density 0.236%

    No Known Activations