© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7000
    Prev
    Next
    INDEX
    Explanations

    negation or contrastive phrases in discussions

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

    Follows conjunctions or contrast words

    np_acts-logits-general · gemini-2.0-flash

    but, since, though

    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
     aber
    -0.62
     entanto
    -0.62
    them
    -0.61
    gdx
    -0.59
    ρων
    -0.58
     jedoch
    -0.58
     Tetapi
    -0.57
     lecz
    -0.56
     Doch
    -0.55
     Porém
    -0.54
    POSITIVE LOGITS
     it
    1.02
     there
    1.01
     unless
    0.98
     frankly
    0.95
     even
    0.94
     if
    0.92
     most
    0.90
     they
    0.85
     you
    0.82
     anything
    0.82
    Activations Density 0.438%

    No Known Activations