© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13214
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal or contractual obligations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Demands or requests for action

    np_acts-logits-general · gemini-2.0-flash

    requesting steps be taken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    Negative Logits
     Occasionally
    -0.44
    Sometimes
    -0.41
     occasionally
    -0.41
     sometimes
    -0.40
     fun
    -0.40
     parfois
    -0.40
    なんとなく
    -0.40
     Sometimes
    -0.39
    sometimes
    -0.38
     иногда
    -0.38
    POSITIVE LOGITS
     urgente
    0.59
     urgently
    0.59
     forthwith
    0.56
    GEBURTSDATUM
    0.54
    )_/¯
    0.51
    InjectAttribute
    0.50
     сро
    0.48
     powinna
    0.47
     should
    0.47
    yfikacja
    0.47
    Activations Density 0.320%

    No Known Activations