© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 3475
    Prev
    Next
    INDEX
    Explanations

    references to military units and organizational structures

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

    numbers and numerical references, particularly related to regiments, military units, and years.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.55
     sufficient
    -0.45
    TagMode
    -0.44
    sendLogPayload
    -0.43
    tagHelperRunner
    -0.43
    faßt
    -0.43
    UMBIA
    -0.41
     extracted
    -0.41
     liệu
    -0.40
     qualitative
    -0.39
    POSITIVE LOGITS
     GenerationType
    0.54
     ExecuteAsync
    0.54
     enää
    0.49
    HomeAsUpEnabled
    0.48
    MigrationBuilder
    0.48
     tokenId
    0.47
    jalá
    0.46
     fédé
    0.46
    PMailer
    0.45
     MainAxisSize
    0.44
    Activations Density 0.576%

    No Known Activations