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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15901
    Prev
    Next
    INDEX
    Explanations

    diagrams and schematic representations related to technical processes and systems

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

    figure references in technical documents, particularly when describing diagrams or illustrations in patent applications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    figure references and technical diagram captions in patent documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.59
    Ecotoxicity
    -0.44
    aarrggbb
    -0.44
    دانشنامهٔ
    -0.43
    verifyException
    -0.41
     EconPapers
    -0.41
    expandindo
    -0.41
     utafitiHapana
    -0.41
     resourceCulture
    -0.41
    RegressionTest
    -0.40
    POSITIVE LOGITS
     diagram
    1.91
     schematic
    1.63
    diagram
    1.61
     Diagram
    1.60
     diagrams
    1.49
    Diagram
    1.49
     DIAGRAM
    1.40
    Schematic
    1.35
     Schematic
    1.34
     sche
    1.27
    Activations Density 0.997%

    No Known Activations