© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7216
    Prev
    Next
    INDEX
    Explanations

    references to legal rules and frameworks, particularly in the context of court cases and submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.52
     يتيمه
    -0.47
    StoryboardSegue
    -0.41
     Wiktionnaire
    -0.41
    webElementGuid
    -0.41
    styleable
    -0.40
     Powell
    -0.40
    tagHelperRunner
    -0.39
    IVEREF
    -0.38
    Powell
    -0.37
    POSITIVE LOGITS
     Pl
    2.33
     PL
    2.30
     Pla
    2.25
    Pl
    2.22
     pl
    2.20
     pla
    2.16
    pl
    2.11
    PL
    2.08
     Plat
    2.02
    Pla
    2.02
    Activations Density 2.168%

    No Known Activations