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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15122
    Prev
    Next
    INDEX
    Explanations

    instances of negation or lack of evidence in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſeveral
    -0.85
     tambi
    -0.73
     ſmall
    -0.69
     alſo
    -0.68
     autorytatywna
    -0.68
     zamiast
    -0.67
    сього
    -0.67
     ſome
    -0.67
     beſt
    -0.66
     ſtill
    -0.66
    POSITIVE LOGITS
     any
    2.42
     anything
    2.35
     anymore
    2.12
    anything
    2.04
     nor
    1.96
     anywhere
    1.91
    any
    1.83
    Any
    1.79
    任何
    1.79
     Any
    1.78
    Activations Density 3.057%

    No Known Activations