© 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. 5-GEMMASCOPE-RES-16K
    11. 5954
    Prev
    Next
    INDEX
    Explanations

    references to the Senate and its members, particularly in discussions of political actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifun
    -0.58
    __':
    -0.58
    意思
    -0.55
     Loh
    -0.55
    <?>>
    -0.54
    IDAD
    -0.53
    yesi
    -0.52
     الري
    -0.51
     cas
    -0.50
     BoxFit
    -0.50
    POSITIVE LOGITS
     senators
    2.02
     senator
    2.01
     Senator
    1.78
     Senators
    1.78
     Senate
    1.72
    Senator
    1.72
     senate
    1.63
     SENATE
    1.52
    Senate
    1.46
     senador
    1.35
    Activations Density 0.150%

    No Known Activations