© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9267
    Prev
    Next
    INDEX
    Explanations

    curly brackets and parentheses in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, numbers, and symbols mixed together

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.30
    lapsingToolbar
    -0.29
    centralwidget
    -0.28
    віти
    -0.26
     bancaire
    -0.26
    aperto
    -0.26
     старости
    -0.24
     való
    -0.23
     voluntad
    -0.23
     justiça
    -0.23
    POSITIVE LOGITS
    ffions
    0.65
    ỽ
    0.64
    niſſe
    0.63
    𓆱
    0.62
    харш
    0.62
    ➟
    0.62
    ⦊
    0.62
    𞤑
    0.61
    ſicht
    0.61
    <unused74>
    0.61
    Activations Density 0.384%

    No Known Activations