© 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. 9459
    Prev
    Next
    INDEX
    Explanations

    references to companies or financial entities

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

    Unusual capitalization and punctuation

    np_acts-logits-general · gemini-2.0-flash

    word beginnings

    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
    <bos>
    -2.08
    JKLM
    -0.64
    juries
    -0.61
    Ayy
    -0.60
    bolt
    -0.59
    ekš
    -0.59
    hob
    -0.58
    %;">
    -0.57
    Selen
    -0.57
    mast
    -0.57
    POSITIVE LOGITS
    zelfde
    0.95
    ی
    0.85
    ه
    0.78
     Wikiseite
    0.77
    iyle
    0.76
    y
    0.74
    י
    0.71
     wikipagina
    0.68
    ième
    0.65
    sweise
    0.63
    Activations Density 4.308%

    No Known Activations