© 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. 41380
    Prev
    Next
    INDEX
    Explanations

    phrases related to police presence and security measures

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

    security personnel and actions

    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
     stroke
    -0.48
     útiles
    -0.45
     essentiel
    -0.43
    stroke
    -0.42
     itinéraires
    -0.42
    ngrx
    -0.42
     useful
    -0.41
     fondateur
    -0.41
     colgante
    -0.41
     enlight
    -0.40
    POSITIVE LOGITS
    AutoScaleMode
    0.54
    verwijspagina
    0.54
    Hentet
    0.45
     AssemblyCompany
    0.42
    Atsauces
    0.39
     saites
    0.38
    发表于
    0.37
     pageContext
    0.37
    __(/*!
    0.37
    asteroide
    0.36
    Activations Density 0.014%

    No Known Activations