© 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. 4951
    Prev
    Next
    INDEX
    Explanations

    phrases related to prior convictions and criminal history

    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
    itans
    -0.49
    Teks
    -0.49
    ējās
    -0.49
     Wikiseite
    -0.46
    Targeted
    -0.46
    Cursors
    -0.45
    ленно
    -0.45
     effetto
    -0.45
     envejec
    -0.45
     identifiant
    -0.44
    POSITIVE LOGITS
     history
    1.68
     previous
    1.45
    history
    1.40
     History
    1.33
    previous
    1.32
     past
    1.31
    History
    1.25
     HISTORY
    1.25
    Previous
    1.24
     Previous
    1.21
    Activations Density 0.906%

    No Known Activations