© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14830
    Prev
    Next
    INDEX
    Explanations

    references to political crimes and accusations related to justice systems

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

    trials or convictions

    np_acts-logits-general · gemini-2.0-flash

    trials and convictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CommonModule
    -0.48
    template
    -0.46
    inescence
    -0.44
    atoare
    -0.43
    …~
    -0.42
     lombok
    -0.41
    CreateModel
    -0.41
    gabung
    -0.41
     CSR
    -0.41
    xmlns
    -0.40
    POSITIVE LOGITS
     trial
    1.72
     prosecution
    1.66
     sentencing
    1.56
     prosecutors
    1.52
     convicted
    1.52
     prosecutions
    1.50
     Trial
    1.49
    trial
    1.49
    Trial
    1.47
     trials
    1.45
    Activations Density 1.683%

    No Known Activations