© 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. 20-GEMMASCOPE-RES-16K
    11. 1138
    Prev
    Next
    INDEX
    Explanations

    phrases related to employment contracts and compensation specifics

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

    Followed by specific nouns or names

    np_acts-logits-general · gemini-2.0-flash

    during or on Earthland

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     esboço
    -0.77
     CreateTagHelper
    -0.75
     typelib
    -0.71
     ***!
    -0.71
     تضيفلها
    -0.69
    IsContent
    -0.68
     defaultstate
    -0.67
    Hentet
    -0.67
     esquecer
    -0.67
    WebVitals
    -0.66
    POSITIVE LOGITS
     etc
    0.74
    ?).
    0.64
    ).
    0.64
    '])->
    0.62
    Спољашње
    0.62
    }$.\\
    0.61
    Enllaces
    0.60
     appunto
    0.59
     }}$.
    0.58
     otherwise
    0.56
    Activations Density 3.171%

    No Known Activations