© 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. 31-GEMMASCOPE-RES-16K
    11. 4554
    Prev
    Next
    INDEX
    Explanations

    references to driving-related legal issues or violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "license" and related phrases about driving violations or vehicle registration.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.68
     ffilmiau
    -0.52
    fjspx
    -0.49
    MigrationBuilder
    -0.45
    adaptiveStyles
    -0.44
    CppMethod
    -0.43
    ITHUB
    -0.43
     Stimm
    -0.42
     jScrollPane
    -0.41
     dõi
    -0.41
    POSITIVE LOGITS
     license
    1.52
     licence
    1.35
     License
    1.34
     plates
    1.24
     plate
    1.23
    license
    1.21
     Licence
    1.18
    License
    1.16
     licenses
    1.13
     licensing
    1.10
    Activations Density 0.107%

    No Known Activations