© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4593
    Prev
    Next
    INDEX
    Explanations

    words related to conflict or opposition, typically involving adversarial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sospe
    -0.44
     mengangg
    -0.41
    cámara
    -0.38
    setVerticalGroup
    -0.38
     agres
    -0.36
     recours
    -0.35
     racc
    -0.35
     fidélité
    -0.34
     coupable
    -0.34
     artificiales
    -0.34
    POSITIVE LOGITS
     defeat
    0.81
     vanqu
    0.77
     annihil
    0.74
     decim
    0.73
     incapac
    0.69
     overthrow
    0.69
     dismantling
    0.69
     dismantle
    0.69
     defeating
    0.68
     annihilated
    0.68
    Activations Density 0.534%

    No Known Activations