© 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. 4-GEMMASCOPE-RES-16K
    11. 11360
    Prev
    Next
    INDEX
    Explanations

    words related to allegations and accusations in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Zgod
    -0.55
    ήσει
    -0.54
    joda
    -0.54
    етра
    -0.53
     Text
    -0.53
    ozof
    -0.53
     extrême
    -0.52
     chré
    -0.52
     Référence
    -0.52
     vasta
    -0.52
    POSITIVE LOGITS
     accuse
    0.81
     accused
    0.68
     accuses
    0.68
    теризу
    0.64
     accusing
    0.63
     gyhoeddwyd
    0.61
     him
    0.61
    TestingModule
    0.61
     ویکی‌پدیا
    0.59
     متعلقه
    0.55
    Activations Density 0.872%

    No Known Activations