© 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. 10279
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to signal processing and computing

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

    preceding "type" or similar terms for categorization

    np_acts-logits-general · gemini-2.0-flash

    types and kinds

    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
    溜
    -0.46
     NDEBUG
    -0.45
    parsedMessage
    -0.44
    лтамалар
    -0.42
     OFDb
    -0.42
    ConstraintMaker
    -0.41
     Archiproducts
    -0.41
    ьаж
    -0.41
     समीक्षक
    -0.41
    Medicine
    -0.40
    POSITIVE LOGITS
     type
    1.18
     types
    1.12
    type
    0.95
     category
    0.92
    类型
    0.89
    类型的
    0.86
    タイプの
    0.84
     jenis
    0.84
     kind
    0.83
     tipo
    0.82
    Activations Density 0.773%

    No Known Activations