© 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. 5799
    Prev
    Next
    INDEX
    Explanations

    elements of performance evaluation and success in various contexts

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

    Text followed by commas

    np_acts-logits-general · gemini-2.0-flash

    passionate ITU nurses, decent numbers, large heads

    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
    Билгалдахарш
    -1.20
     nahilalakip
    -1.14
    GEBURTSDATUM
    -1.14
     linkovi
    -1.12
     itſelf
    -1.12
     bezeichneter
    -1.08
     propOrder
    -1.06
     autorytatywna
    -1.05
    AutoresizingMask
    -1.03
    Vidite
    -1.03
    POSITIVE LOGITS
     
    0.84
    ,
    0.68
    .
    0.67
     (
    0.67
    ↵↵
    0.63
    -
    0.63
     "
    0.62
     M
    0.61
     $\
    0.60
     -
    0.60
    Activations Density 5.124%

    No Known Activations