© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10684
    Prev
    Next
    INDEX
    Explanations

    references to opinions or reactions regarding interpersonal discussions or debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     planificación
    -0.51
    NameInMap
    -0.49
     prioridad
    -0.47
     Supervision
    -0.45
     recuperación
    -0.45
    IVEREF
    -0.45
    Supervision
    -0.44
     ویکی‌پدی
    -0.44
     cooperación
    -0.44
    хьтан
    -0.43
    POSITIVE LOGITS
     arguments
    0.49
     debate
    0.47
    debate
    0.46
     disagreeable
    0.46
     discredit
    0.45
     cliquez
    0.43
     argumentos
    0.42
     disagreed
    0.42
    期刊论文
    0.41
     debates
    0.41
    Activations Density 0.874%

    No Known Activations