© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15208
    Prev
    Next
    INDEX
    Explanations

    blocks of code, specifically looking for braces and comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }-${
    -0.56
     שוליים
    -0.55
    IContainer
    -0.54
    Datuak
    -0.54
    openqa
    -0.52
    right
    -0.51
     trading
    -0.51
    ends
    -0.50
     sea
    -0.50
    QtGui
    -0.49
    POSITIVE LOGITS
    IsMutable
    0.60
    GEBURTSDATUM
    0.60
     مرئيه
    0.59
    تفصیلات
    0.59
    WithIOException
    0.59
    mobileqq
    0.58
    AddTagHelper
    0.54
    mybatisplus
    0.54
    InputTagHelper
    0.53
     lezioni
    0.53
    Activations Density 0.231%

    No Known Activations