© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12541
    Prev
    Next
    INDEX
    Explanations

    discussions involving ethical or moral dilemmas

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

    Arguments, debates, and disagreements

    np_acts-logits-general · gemini-2.0-flash

    accuses, debates, or argues

    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
    labelledby
    -0.58
    PreAuthorize
    -0.56
    ientôt
    -0.52
    urlpatterns
    -0.50
     secreta
    -0.48
     AssemblyVersion
    -0.48
     planea
    -0.47
    حياتها
    -0.47
    cheduled
    -0.47
    Ofic
    -0.46
    POSITIVE LOGITS
     argument
    1.22
     arguments
    1.15
     arguing
    1.11
     argumento
    1.10
     argumentos
    1.02
    argument
    1.00
     rebuttal
    0.98
     Argument
    0.94
     argue
    0.93
    arguments
    0.93
    Activations Density 0.912%

    No Known Activations