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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 6875
    Prev
    Next
    INDEX
    Explanations

    statements related to police involvement or actions in various scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     चीज़ों
    -0.68
     AssemblyVersion
    -0.64
     AssemblyTitle
    -0.63
    Espèce
    -0.61
     CreateTagHelper
    -0.61
    setVerticalGroup
    -0.59
    AndEndTag
    -0.57
    propTypes
    -0.55
    ViewImports
    -0.54
    tagext
    -0.54
    POSITIVE LOGITS
     police
    2.33
    police
    1.88
     Police
    1.82
    Police
    1.74
     POLICE
    1.57
     cops
    1.56
     policemen
    1.49
     policía
    1.42
     authorities
    1.36
    警察
    1.33
    Activations Density 0.316%

    No Known Activations