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. 24-GEMMASCOPE-RES-16K
    6. 4424
    Prev
    Next
    INDEX
    Explanations

    phrases that express skepticism or criticism towards economic systems and societal entitlement

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

    Sarcastic or dismissive language

    np_acts-logits-general · gemini-2.0-flash

    rubbish, lies, nonsense, crap

    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
    tvguidetime
    -0.90
     rayures
    -0.87
     purpoſe
    -0.71
     Grecs
    -0.67
     fubject
    -0.65
     giustizia
    -0.64
     inesper
    -0.64
     uſe
    -0.63
     enfans
    -0.63
     Wikimedijinoj
    -0.62
    POSITIVE LOGITS
     nonsense
    1.15
     BS
    1.02
     bullshit
    1.01
     dri
    0.90
     crap
    0.89
    nonsense
    0.88
     gibber
    0.86
     pontific
    0.84
     bs
    0.84
     whining
    0.83
    Activations Density 0.414%

    No Known Activations