© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16056
    Prev
    Next
    INDEX
    Explanations

    locations and entities associated with Nevada

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

    Nevada and Las Vegas locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    TargetException
    -0.65
     GenerationType
    -0.65
     виправивши
    -0.59
    Reprodução
    -0.58
    AxisAlignment
    -0.57
     оригіналу
    -0.57
    izoen
    -0.57
    ScopeManager
    -0.57
    verwijspagina
    -0.57
    XmlAccessorType
    -0.56
    POSITIVE LOGITS
     Nevada
    1.16
    Nevada
    1.03
     nevada
    0.82
     Vegas
    0.81
     VEGAS
    0.70
    vegas
    0.63
     vegas
    0.63
    Vegas
    0.62
     Mojave
    0.62
     Las
    0.61
    Activations Density 0.031%

    No Known Activations