© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9712
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and judicial concepts

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

    Following "for", "as", "if", or "except"

    np_acts-logits-general · gemini-2.0-flash

    except whether

    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
     myſelf
    -0.75
     étoit
    -0.75
     purpoſe
    -0.71
     neceff
    -0.70
     uſe
    -0.67
     Efq
    -0.66
     pleaſure
    -0.65
     viſ
    -0.65
     étoient
    -0.65
     Monfieur
    -0.65
    POSITIVE LOGITS
    HtmlAttribute
    0.60
    เรื่อง
    0.57
    usten
    0.55
    LookAnd
    0.52
    ContentAsync
    0.52
     others
    0.52
     physical
    0.52
    Concerning
    0.49
    namely
    0.49
     pinulongan
    0.49
    Activations Density 1.068%

    No Known Activations