Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 228
    Prev
    Next
    INDEX
    Explanations

    references to investigations into Hillary Clinton and related political actions

    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
     parli
    -0.52
    hlands
    -0.52
    MemoryWarning
    -0.51
    MessageTagHelper
    -0.51
     שוליים
    -0.51
     transfieras
    -0.50
    jooq
    -0.48
     Monza
    -0.46
     Parli
    -0.46
     parliamentary
    -0.46
    POSITIVE LOGITS
     department
    0.86
     Department
    0.84
     Clinton
    0.81
     Hillary
    0.77
    Clinton
    0.76
    department
    0.76
    Hillary
    0.76
     département
    0.75
    Department
    0.75
     Secretary
    0.75
    Activations Density 0.238%

    No Known Activations