Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9030
    Prev
    Next
    INDEX
    Explanations

    references to specific days of the week and notable figures

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

    preceding possessive punctuation

    np_acts-logits-general · gemini-2.0-flash

    possessive forms

    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
     بيها
    -0.53
    äldrar
    -0.51
    calaureate
    -0.49
    ็จ
    -0.48
     ModelExpression
    -0.48
    TypedDataSet
    -0.47
    uyez
    -0.47
    cinoma
    -0.47
    niająca
    -0.46
    pencer
    -0.46
    POSITIVE LOGITS
    ’
    1.86
    '
    1.73
    $'
    1.40
    의
    1.03
    ´
    0.96
    \'
    0.95
    <bos>
    0.92
    }'
    0.86
    ’
    0.85
    ‟
    0.84
    Activations Density 1.830%

    No Known Activations