© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6180
    Prev
    Next
    INDEX
    Explanations

    terms related to legal classifications and regulations, particularly concerning marijuana and expressions of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.61
    evos
    -0.56
     Safety
    -0.52
     veiligheid
    -0.51
    MigrationBuilder
    -0.48
    safety
    -0.48
    Бележки
    -0.47
     bezpiecze
    -0.46
    Safety
    -0.46
     Administrativna
    -0.46
    POSITIVE LOGITS
    /**
    0.65
     Arki
    0.65
    PyExc
    0.61
     BoxDecoration
    0.59
     fieldNum
    0.57
    cerely
    0.56
    jectures
    0.56
    createCell
    0.56
     ddelweddau
    0.55
    enumii
    0.55
    Activations Density 1.041%

    No Known Activations