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. 16-GEMMASCOPE-RES-16K
    6. 5187
    Prev
    Next
    INDEX
    Explanations

    questions related to measurements and conversions between different units

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

    Conversion of units, often to nanograms

    np_acts-logits-general · gemini-2.0-flash

    large numbers or scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ✭✭
    -0.61
     saites
    -0.60
    ('/:
    -0.59
    tvguidetime
    -0.58
     pinulongan
    -0.56
     خارجية
    -0.55
    τευ
    -0.54
    /");
    -0.54
    Географи
    -0.53
    Билгалдахарш
    -0.53
    POSITIVE LOGITS
     thousand
    0.77
     thousands
    0.71
     hundreds
    0.68
     million
    0.67
     Thousand
    0.65
     millions
    0.62
     Thousands
    0.61
     Hundreds
    0.59
     Millions
    0.58
     THOUS
    0.57
    Activations Density 1.320%

    No Known Activations