© 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. 18-GEMMASCOPE-RES-16K
    11. 7235
    Prev
    Next
    INDEX
    Explanations

    instances of confinement or restrictions placed on individuals

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

    Prison/jail conditions and restrictions

    np_acts-logits-general · gemini-2.0-flash

    food and restrictions in confinement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.84
    
    -0.79
    󠁢
    -0.77
     utafitiHapana
    -0.77
     }}"></
    -0.77
    mappedBy
    -0.77
     snippetHide
    -0.67
    Viitteet
    -0.67
     متعلقه
    -0.67
     שוליים
    -0.67
    POSITIVE LOGITS
     daily
    0.90
     rations
    0.76
    daily
    0.75
     ration
    0.69
     nightly
    0.63
     bunk
    0.62
     meals
    0.62
     food
    0.58
    每天
    0.57
    Meals
    0.55
    Activations Density 0.382%

    No Known Activations