© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4259
    Prev
    Next
    INDEX
    Explanations

    key phrases and phrases indicating major factors, implications, or differences in discussions

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

    before "is" or "with"

    np_acts-logits-general · gemini-2.0-flash

    problems and positive aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.77
    ImageContext
    -0.74
    multer
    -0.72
    iſchen
    -0.71
    RegressionTest
    -0.71
    ſelben
    -0.70
     erſten
    -0.69
    久しぶ
    -0.69
     ſeyn
    -0.69
     queſta
    -0.68
    POSITIVE LOGITS
    帖最后由
    0.33
     encargada
    0.27
     encargado
    0.25
    会上
    0.23
     sahibi
    0.23
     meeting
    0.23
     voir
    0.23
    Parameteri
    0.22
     gången
    0.22
     He
    0.21
    Activations Density 0.881%

    No Known Activations