© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6744
    Prev
    Next
    INDEX
    Explanations

    acronyms and organizational names related to police and law enforcement agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tenga
    -0.43
     Haben
    -0.37
     pièce
    -0.32
     Manns
    -0.32
     tener
    -0.31
     ferons
    -0.31
     Seite
    -0.31
     Compañ
    -0.30
    very
    -0.30
     bonos
    -0.30
    POSITIVE LOGITS
    RenderAtEndOf
    0.78
    WriteTagHelper
    0.77
    expandindo
    0.73
     MainAxisSize
    0.71
     AssemblyCulture
    0.70
    OGND
    0.69
    genodigd
    0.69
     ModelExpression
    0.68
    AddHtmlAttribute
    0.67
    IsMutable
    0.65
    Activations Density 0.491%

    No Known Activations