© 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. 20-GEMMASCOPE-RES-16K
    6. 15258
    Prev
    Next
    INDEX
    Explanations

    references to the dictatorship of the proletariat and its significance in revolutionary theory

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

    Marxism and class struggle

    np_acts-logits-general · gemini-2.0-flash

    capitalist accumulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     perd
    -0.52
    wyk
    -0.48
    ligible
    -0.47
     radon
    -0.44
    ræ
    -0.41
    ylate
    -0.41
    AddRange
    -0.41
     حرم
    -0.41
    ETY
    -0.41
    umatic
    -0.41
    POSITIVE LOGITS
     capitalist
    1.19
     capitalism
    1.14
     capitalists
    1.09
    Capital
    1.09
    capital
    1.07
     Capitalism
    1.03
     Capital
    1.01
     kapital
    0.97
     capital
    0.96
     CAPITAL
    0.95
    Activations Density 0.238%

    No Known Activations