© 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. 47926
    Prev
    Next
    INDEX
    Explanations

    references to locations and chemical compounds, particularly focusing on "Atlanta" and "ATP."

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

    ATP and Atlanta related terms

    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
    VersionUID
    -0.67
    ReusableCell
    -0.59
     Numerade
    -0.59
     nahilalakip
    -0.57
    PyExc
    -0.57
     jengibre
    -0.55
    cestershire
    -0.53
     trovar
    -0.53
    codable
    -0.52
     simplifié
    -0.52
    POSITIVE LOGITS
     Atkinson
    0.68
     at
    0.65
     At
    0.63
     Atkins
    0.63
    At
    0.62
    at
    0.62
     Atlanta
    0.62
     Atelier
    0.60
     AT
    0.59
     Att
    0.58
    Activations Density 0.032%

    No Known Activations