© 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. 20-GEMMASCOPE-RES-16K
    11. 8690
    Prev
    Next
    INDEX
    Explanations

    mention of specific materials and their characteristics in the context of technical processes

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

    This neuron identifies when nouns are preceded by "the" in technical and scientific contexts.

    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
    Psalm
    -0.35
    XtraEditors
    -0.34
    RSpec
    -0.34
    paraiso
    -0.34
    VCR
    -0.34
     asegurarse
    -0.33
    nmgp
    -0.33
    verwijspagina
    -0.33
    locaust
    -0.32
    flash
    -0.32
    POSITIVE LOGITS
     AssemblyCulture
    0.60
    writeFieldEnd
    0.58
    StructEnd
    0.56
    aarrggbb
    0.55
     ویکی‌پدی
    0.54
    DockStyle
    0.52
    RTHOOK
    0.52
    sprzedam
    0.52
    exitRule
    0.52
    usercontent
    0.49
    Activations Density 0.679%

    No Known Activations