© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10600
    Prev
    Next
    INDEX
    Explanations

    comments and annotations related to coding and programming concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Code-related terms and Java code

    np_acts-logits-general · gemini-2.0-flash

    foreign words and location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    <strong>
    -0.65
     AssemblyCulture
    -0.58
    Uninitialized
    -0.55
    WebControls
    -0.55
    <code>
    -0.55
    styleType
    -0.53
    tagHelperRunner
    -0.53
    AccessorTable
    -0.53
    CppMethod
    -0.52
    ="#"><
    -0.52
    POSITIVE LOGITS
    adaptiveStyles
    0.68
     wegen
    0.66
     ours
    0.62
     FIXME
    0.62
    こっち
    0.61
     daqui
    0.60
     here
    0.60
     Ours
    0.59
    zeba
    0.59
    енча
    0.58
    Activations Density 0.702%

    No Known Activations