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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 3744
    Prev
    Next
    INDEX
    Explanations

    references to influential Marxist figures and their ideologies

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

    proletariat or class struggle

    np_acts-logits-general · gemini-2.0-flash

    proletarian dictatorship and class struggle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     privacy
    -0.42
     Privacy
    -0.41
    chevêque
    -0.41
    ionView
    -0.40
    compliance
    -0.39
     
    -0.38
     xếp
    -0.38
     "+
    -0.37
     حرم
    -0.37
    натор
    -0.36
    POSITIVE LOGITS
     Marxist
    1.10
     Marx
    1.09
     EconPapers
    1.08
    Marx
    1.04
     Trotsky
    0.96
     prolet
    0.96
     marx
    0.95
     Lenin
    0.94
    Lenin
    0.93
     Workers
    0.92
    Activations Density 0.366%

    No Known Activations