Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12906
    Prev
    Next
    INDEX
    Explanations

    historical events related to uprisings and revolutions

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

    uprisings and rebellions

    np_acts-logits-general · gemini-2.0-flash

    uprising and rebellion vocabulary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respecter
    -0.49
    ArgsConstructor
    -0.48
     Predators
    -0.45
    Jîn
    -0.44
    asio
    -0.43
    Expert
    -0.42
     tonel
    -0.42
    xtext
    -0.41
     Warming
    -0.41
    尴尬
    -0.41
    POSITIVE LOGITS
     rebellion
    1.73
     revolt
    1.70
     rebel
    1.57
     resistance
    1.54
     uprising
    1.45
     rebels
    1.43
    rebel
    1.39
     Revolt
    1.39
     Rebellion
    1.38
     insurrection
    1.35
    Activations Density 0.495%

    No Known Activations