© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 16059
    Prev
    Next
    INDEX
    Explanations

    references to political rhetoric and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.71
    WebElementEntity
    -0.61
    addContainerGap
    -0.46
     rapidity
    -0.45
    tizia
    -0.45
     sagde
    -0.44
    Wikis
    -0.42
     Wayback
    -0.42
     Wiktionnaire
    -0.42
     addirittura
    -0.41
    POSITIVE LOGITS
     selama
    1.02
     bisherigen
    0.91
     hitherto
    0.91
     heretofore
    0.89
     bisher
    0.84
     previously
    0.83
     протяжении
    0.82
     bislang
    0.77
     previous
    0.77
    Selama
    0.76
    Activations Density 0.294%

    No Known Activations