© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13939
    Prev
    Next
    INDEX
    Explanations

    references to non-profit organizations and charitable donations by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Afterward
    -0.54
    ſelves
    -0.53
     ſeveral
    -0.52
    更好地
    -0.50
     dasselbe
    -0.50
     stället
    -0.50
     Asimismo
    -0.48
     poffible
    -0.48
     tranſ
    -0.47
     neceſſ
    -0.47
    POSITIVE LOGITS
     utafitiHapana
    0.75
     loosing
    0.73
     HasFactory
    0.71
    ConstraintMaker
    0.69
     dimana
    0.68
    慢慢的
    0.66
     todays
    0.65
     didalam
    0.64
    Lets
    0.64
     Whilst
    0.63
    Activations Density 1.945%

    No Known Activations