© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5479
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming constructs related to data structures and API interactions

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

    Tokens before certain words: packages, classes, records, files

    np_acts-logits-general · gemini-2.0-flash

    programming constructs or data entity names

    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
     internetowa
    -0.54
    æus
    -0.53
    æa
    -0.51
    wicz
    -0.50
    ardi
    -0.49
    ś
    -0.49
    انة
    -0.48
    rivial
    -0.48
    ič
    -0.48
    上一
    -0.48
    POSITIVE LOGITS
     jotka
    0.85
    hips
    0.84
     تانيه
    0.72
     våre
    0.71
     которые
    0.69
     themselves
    0.68
     themſelves
    0.68
     мәкал
    0.68
    SharedDtor
    0.68
     които
    0.67
    Activations Density 0.281%

    No Known Activations