© 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 EvalsExportsinterp-engineNEWAPI 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. 6569
    Prev
    Next
    INDEX
    Explanations

    recommendations and positive evaluations of books

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

    necessity or requirement

    np_acts-logits-general · gemini-2.0-flash

    necessity or strong recommendation

    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
    KommentareTeilen
    -0.47
    wnież
    -0.43
     Tuch
    -0.42
    nein
    -0.41
    Batis
    -0.39
     InputDecoration
    -0.39
     Dafür
    -0.38
     مشين
    -0.37
     INTEGR
    -0.36
     iNdEx
    -0.36
    POSITIVE LOGITS
     MUST
    0.77
     must
    0.73
     حتما
    0.69
     wajib
    0.69
     worth
    0.69
     should
    0.68
    MUST
    0.67
     warto
    0.66
     обязательно
    0.66
    must
    0.65
    Activations Density 0.199%

    No Known Activations