© 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. 30-GEMMASCOPE-RES-16K
    11. 13341
    Prev
    Next
    INDEX
    Explanations

    technical terms and constructs used in programming and software development

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

    Swift Protobuf implementation details

    np_acts-logits-general · gemini-2.0-flash

    protobuf `unique` storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.44
    ismet
    -0.44
    abetes
    -0.43
     ✭✭
    -0.42
     Patch
    -0.39
    adaptiveStyles
    -0.38
     cape
    -0.38
    NOPQRST
    -0.38
    ướ
    -0.36
    Patch
    -0.36
    POSITIVE LOGITS
    UrlResolution
    0.66
     ModelExpression
    0.54
    AntiForgeryToken
    0.54
     '\\;'
    0.51
    хьтан
    0.50
    UnusedPrivate
    0.49
     lenker
    0.49
    interopRequire
    0.47
    TagNumber
    0.47
     оригіналу
    0.47
    Activations Density 1.971%

    No Known Activations