© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 16016
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of text segments or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    <strong>
    -0.40
    lässlich
    -0.32
     pungkas
    -0.31
    <b>
    -0.31
     pungkasnya
    -0.30
    <h1>
    -0.30
     pēc
    -0.29
     complementos
    -0.29
    最近
    -0.28
    Londres
    -0.27
    POSITIVE LOGITS
    <unused52>
    1.15
    [@BOS@]
    1.15
    <unused28>
    1.14
    <unused14>
    1.14
    <unused68>
    1.14
    <unused79>
    1.14
    <unused8>
    1.14
    <unused21>
    1.13
    <unused16>
    1.13
    <unused3>
    1.13
    Activations Density 0.207%

    No Known Activations