© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 38
    Prev
    Next
    INDEX
    Explanations

    references to disclosures in legal contexts

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

    instances of the term "disclosure" and its variations

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

    disclosure of required information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nya
    -0.61
    jface
    -0.59
    E
    -0.56
    1
    -0.55
    6
    -0.52
    knecht
    -0.52
     ๆ
    -0.51
    5
    -0.51
    N
    -0.51
     
    -0.50
    POSITIVE LOGITS
     InputDecoration
    1.13
    rungsseite
    0.90
     Efq
    0.87
    )");
    0.83
     purpoſe
    0.83
    IsContent
    0.82
     gynhyrchwyd
    0.82
    MLLoader
    0.79
     متعلقه
    0.79
     myſelf
    0.79
    Activations Density 0.025%

    No Known Activations