© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 563
    Prev
    Next
    INDEX
    Explanations

    terms related to crime and criminal investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéia
    -0.78
     pessoal
    -0.43
    IVEREF
    -0.43
    rungsseite
    -0.42
     opinião
    -0.41
     vuestro
    -0.41
    Diweddarwch
    -0.41
     Verfügung
    -0.40
    請繼續往下閱讀
    -0.40
    iterranée
    -0.40
    POSITIVE LOGITS
     GoFundMe
    0.68
     woman
    0.64
     SUV
    0.63
     pitbull
    0.63
     suspected
    0.62
     suspect
    0.62
     motorist
    0.61
     TikTok
    0.60
     Airbnb
    0.58
     homeless
    0.58
    Activations Density 0.287%

    No Known Activations