© 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. 5554
    Prev
    Next
    INDEX
    Explanations

    technical specifications and terminology related to vehicle engines and software functions

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

    Tokens before capitalized words

    np_acts-logits-general · gemini-2.0-flash

    Le Quesne, Doussal, Porth Wen

    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
    Espèce
    -0.82
     Efq
    -0.67
    ChildScrollView
    -0.67
     pylint
    -0.66
     AttributeSet
    -0.63
    ConstraintMaker
    -0.62
    mergeFrom
    -0.61
     againſt
    -0.61
     convertView
    -0.60
     himſelf
    -0.60
    POSITIVE LOGITS
     Insee
    0.49
    aarrggbb
    0.46
    enn
    0.45
     vite
    0.43
    vite
    0.43
     рай
    0.43
    وزيع
    0.42
     noten
    0.42
    ς
    0.41
    ⎩
    0.41
    Activations Density 0.128%

    No Known Activations