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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14873
    Prev
    Next
    INDEX
    Explanations

    concepts related to scientific measurements and analyses

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

    followed by "was," "has," or a comma

    np_acts-logits-general · gemini-2.0-flash

    cells, genes, genome, growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     فريبيس
    -0.54
    DockStyle
    -0.52
    الإنجليزية
    -0.51
    +#+
    -0.50
    OGND
    -0.49
     ویکی‌پدیای
    -0.48
    󠁣
    -0.46
    writeFieldEnd
    -0.46
     تضيفلها
    -0.45
    seigneur
    -0.44
    POSITIVE LOGITS
    uxxxx
    2.03
    weightedMode
    0.81
     editText
    0.76
    InstrumentedTest
    0.74
     MemoryStream
    0.69
    InjectAttribute
    0.67
    .*")]
    0.59
    numeros
    0.52
    parsedMessage
    0.46
    WillAppear
    0.44
    Activations Density 2.024%

    No Known Activations