© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13730
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Brazilian political scandal events

    np_acts-logits-general · gemini-2.0-flash

    political accusations and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arose
    -0.57
     occurred
    -0.56
     consisted
    -0.55
     coincided
    -0.52
     existed
    -0.52
     Chwiliwch
    -0.51
     đã
    -0.51
     occured
    -0.51
     telah
    -0.50
    appeared
    -0.49
    POSITIVE LOGITS
     becomes
    1.16
     gets
    1.14
     goes
    1.04
     takes
    1.02
     begins
    0.97
     decides
    0.96
     starts
    0.92
     receives
    0.90
     arrives
    0.90
     develops
    0.89
    Activations Density 1.638%

    No Known Activations