© 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. 9-GEMMASCOPE-RES-16K
    11. 10192
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate opposition or resistance to various entities or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.77
     pleaſure
    -0.72
     houſe
    -0.67
     Majefty
    -0.61
     purpoſe
    -0.61
     Plenum
    -0.59
     scolas
    -0.56
     poffe
    -0.56
    URLException
    -0.56
    LLocation
    -0.54
    POSITIVE LOGITS
     against
    2.11
     Against
    2.00
    Against
    1.97
    against
    1.95
     AGAINST
    1.87
     gegen
    1.37
     contre
    1.23
     против
    1.15
     melawan
    1.11
     נגד
    1.10
    Activations Density 0.099%

    No Known Activations