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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1
    Prev
    Next
    INDEX
    Explanations

    financial performance indicators and metrics

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

    Financial reports and quarters

    np_acts-logits-general · gemini-2.0-flash

    fiscal earnings and quarterly reports

    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
    Personendaten
    -0.56
     local
    -0.54
    AsUp
    -0.52
     Local
    -0.52
     εγ
    -0.49
    DoubleQuotes
    -0.49
     utafitiHapana
    -0.49
    солю
    -0.47
     FileReader
    -0.47
    urança
    -0.46
    POSITIVE LOGITS
     earnings
    0.89
     Earnings
    0.83
    earnings
    0.74
    Earnings
    0.73
    MarshalTo
    0.68
    CFO
    0.60
     profits
    0.58
     CFO
    0.58
     quarterly
    0.56
    ArrowToggle
    0.56
    Activations Density 0.125%

    No Known Activations