Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 179
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement entities, particularly police

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.68
    tagHelperRunner
    -0.62
     ujednoznacz
    -0.57
     Chwiliwch
    -0.57
     Roskov
    -0.56
     πρά
    -0.53
    EndInit
    -0.51
     itemView
    -0.50
    contentLoaded
    -0.50
     Hou
    -0.50
    POSITIVE LOGITS
     officers
    0.88
    Officers
    0.87
     officer
    0.80
    officer
    0.77
    officers
    0.76
     OFFICERS
    0.76
     OFFICER
    0.73
     Officers
    0.71
     judiciaire
    0.66
     force
    0.64
    Activations Density 0.060%

    No Known Activations