© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 54511
    Prev
    Next
    INDEX
    Explanations

    references to trials and legal proceedings

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

    crime news and trials

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects proper names of notable people, especially high-profile individuals mentioned in media, trials, or news contexts.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.40
    krut
    -0.39
     femininas
    -0.36
    gebob
    -0.36
    僕が
    -0.36
     Sahne
    -0.35
     AssemblyCompany
    -0.35
     nacionais
    -0.35
     hydro
    -0.34
     FontAwesome
    -0.34
    POSITIVE LOGITS
    RegressionTest
    0.60
    itinéraire
    0.55
    PullParser
    0.47
    ⓧ
    0.47
    IndentedString
    0.45
    enderror
    0.44
    MigrationBuilder
    0.44
     Verfü
    0.44
     Autorizaciones
    0.43
     disambiguazione
    0.42
    Activations Density 0.301%

    No Known Activations