© 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. 12609
    Prev
    Next
    INDEX
    Explanations

    numerical values or identifiers, particularly in the context of patents or technical specifications

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

    U.S. patent numbers and references in legal/technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
     preſent
    -0.49
    ckså
    -0.44
     étoit
    -0.40
     ſtill
    -0.38
     ſta
    -0.36
     ſche
    -0.35
     adverten
    -0.35
     feroit
    -0.34
     gâteau
    -0.34
    jangkau
    -0.34
    POSITIVE LOGITS
     ब्रेकडाउन
    0.73
    RegressionTest
    0.66
    хьтан
    0.60
    FunctionFlags
    0.59
    DeleteBehavior
    0.57
     Biôgrafia
    0.56
     ligiloj
    0.56
    OGND
    0.56
    يكب
    0.55
     transfieras
    0.55
    Activations Density 0.257%

    No Known Activations