© 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. 16-GEMMASCOPE-RES-16K
    11. 7194
    Prev
    Next
    INDEX
    Explanations

    legal terminology and formal court procedures

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

    Tokens indicating conclusions or affirmations

    np_acts-logits-general · gemini-2.0-flash

    affirming or reversing decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jspx
    -0.55
    httphttps
    -0.53
    culously
    -0.51
    owatt
    -0.49
    Ideally
    -0.47
    BASEPATH
    -0.47
    UrlResolution
    -0.47
     swear
    -0.46
    erialized
    -0.46
    сон
    -0.45
    POSITIVE LOGITS
     accordingly
    0.72
     provisoire
    0.68
     therefore
    0.65
     conséquence
    0.65
     تضيفلها
    0.65
    Personensuche
    0.63
     hereby
    0.61
     conclude
    0.60
     portanto
    0.59
    GEBURTSDATUM
    0.59
    Activations Density 1.406%

    No Known Activations