© 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. 15403
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation in text

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

    Token before bracketed expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with closing delimiters

    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
    gouv
    -0.64
    న్న
    -0.61
     parte
    -0.59
     Morrison
    -0.59
    дование
    -0.58
    ariot
    -0.58
     di
    -0.58
    нциклопе
    -0.55
    افع
    -0.54
     Parte
    -0.54
    POSITIVE LOGITS
     ―――――
    0.92
    出版年
    0.89
     myſelf
    0.88
     raiſ
    0.86
     ſind
    0.85
     Shakspeare
    0.84
     itſelf
    0.83
     greateſt
    0.83
     Verſ
    0.81
     doubtnut
    0.81
    Activations Density 0.805%

    No Known Activations