© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 382
    Prev
    Next
    INDEX
    Explanations

    numbers and their associated quantities

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

    Numbers followed by other numbers

    np_acts-logits-general · gemini-2.0-flash

    numerical data sequences

    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
     Савезне
    -0.74
    PreferredItem
    -0.63
    PerformLayout
    -0.58
    mtrl
    -0.58
     adulta
    -0.54
    ViewImports
    -0.52
    ikala
    -0.51
     Ums
    -0.51
    )$_
    -0.51
    AsUp
    -0.51
    POSITIVE LOGITS
     Partagez
    0.49
    SourceChecksum
    0.48
    下载附件
    0.46
    रीद
    0.46
     Mean
    0.45
     Dead
    0.44
    erker
    0.44
     dead
    0.43
     Sal
    0.42
    anka
    0.42
    Activations Density 0.421%

    No Known Activations