© 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. 17-GEMMASCOPE-RES-16K
    6. 1457
    Prev
    Next
    INDEX
    Explanations

    references to economic and political power structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    preso
    -0.52
     meilleures
    -0.50
     melhores
    -0.49
     disambiguazione
    -0.48
     chaus
    -0.48
     approachable
    -0.48
     Meille
    -0.48
    спонд
    -0.47
     <>",
    -0.46
    inquirer
    -0.46
    POSITIVE LOGITS
     neoliberal
    0.72
     billions
    0.68
    endwhile
    0.65
     greedy
    0.65
     artificially
    0.65
    artificial
    0.65
     artificial
    0.65
     olig
    0.64
     greed
    0.63
     capitalist
    0.63
    Activations Density 0.799%

    No Known Activations