© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8801
    Prev
    Next
    INDEX
    Explanations

    references to social injustices and discrimination

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

    Types of abuse/discrimination

    np_acts-logits-general · gemini-2.0-flash

    commission of harms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodedInputStream
    -0.61
     referenties
    -0.61
    InvalidProtocol
    -0.59
     importance
    -0.55
     surla
    -0.55
    +#+#
    -0.55
    ährlich
    -0.54
    inally
    -0.53
    gypti
    -0.50
    Importance
    -0.50
    POSITIVE LOGITS
     committed
    1.19
     perpetrated
    1.12
     Committed
    0.94
     practiced
    0.92
     practised
    0.89
     perpetuated
    0.89
     directed
    0.86
    committed
    0.86
     levelled
    0.78
     commit
    0.77
    Activations Density 0.442%

    No Known Activations