© 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. 22-GEMMASCOPE-RES-16K
    11. 678
    Prev
    Next
    INDEX
    Explanations

    elements related to legal restrictions and discrimination in practices

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

    Preceding words related to legal or ethical violations

    np_acts-logits-general · gemini-2.0-flash

    unfairness, discrimination, violation of rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
     незавершена
    -0.57
    Népesség
    -0.57
    θος
    -0.55
     decompose
    -0.54
     decomposition
    -0.54
     decomposed
    -0.53
    GeoNames
    -0.51
     myſelf
    -0.51
     stimmt
    -0.51
     بيها
    -0.51
    POSITIVE LOGITS
     arbitrary
    1.03
     arbitrarily
    0.98
     unfairly
    0.90
     discriminatory
    0.90
    arbitrary
    0.87
     punitive
    0.83
     arbitrar
    0.82
     Arbitrary
    0.82
     unfair
    0.80
     capricious
    0.78
    Activations Density 0.785%

    No Known Activations