© 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. 9287
    Prev
    Next
    INDEX
    Explanations

    specific names and entities related to individuals and organizations

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

    Hexadecimal representations (0x...)

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers and Arabic text

    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
    ない
    -0.71
     său
    -0.57
    nya
    -0.53
    liśmy
    -0.52
    tif
    -0.51
    l
    -0.50
    n
    -0.50
    <tr>
    -0.50
    ţional
    -0.50
     Valentín
    -0.50
    POSITIVE LOGITS
    ا
    0.80
    a
    0.71
    اا
    0.69
    اااا
    0.66
    aaaa
    0.63
    e
    0.61
    aaa
    0.61
    aa
    0.59
    erba
    0.59
    ぁ
    0.56
    Activations Density 1.327%

    No Known Activations