© 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. 7273
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal documentation and formal agreements

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

    Written or codified agreements

    np_acts-logits-general · gemini-2.0-flash

    documented in writing

    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
     Administrativna
    -0.65
    richTextPanel
    -0.54
    UrlResolution
    -0.46
     contextLoads
    -0.44
    ributor
    -0.44
    FRC
    -0.44
     Roskov
    -0.43
    gië
    -0.43
    IonicModule
    -0.42
     VizieR
    -0.42
    POSITIVE LOGITS
     written
    1.91
     Written
    1.59
    written
    1.59
     WRITTEN
    1.58
    Written
    1.55
     schrift
    1.49
     escrito
    1.37
     writing
    1.36
     skrift
    1.32
     écrite
    1.31
    Activations Density 0.355%

    No Known Activations