© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12620
    Prev
    Next
    INDEX
    Explanations

    references to historical secret societies and their influence

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

    Organizations or groups

    np_acts-logits-general · gemini-2.0-flash

    brotherhood and lodges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.70
    ագրություններ
    -0.62
     ModelExpression
    -0.56
    eltzer
    -0.56
     Eurosport
    -0.55
    EndContext
    -0.54
    الحياه
    -0.53
    InitVars
    -0.52
    EndGlobalSection
    -0.51
     دیکھیے
    -0.50
    POSITIVE LOGITS
     lodge
    1.00
     Lodge
    0.92
     lodges
    0.89
     fraternal
    0.85
    Brother
    0.79
    lodge
    0.77
     Brother
    0.75
     Masonic
    0.73
    brother
    0.73
     Grand
    0.73
    Activations Density 0.111%

    No Known Activations