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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 16207
    Prev
    Next
    INDEX
    Explanations

    financial metrics and indicators related to stock performance

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

    Financial calculations or formulas

    np_acts-logits-general · gemini-2.0-flash

    stock valuation and returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.73
    BeginContext
    -0.69
    SqlSession
    -0.67
    AndEndTag
    -0.67
     linkovi
    -0.65
     ComVisible
    -0.64
    MLLoader
    -0.62
    awtextra
    -0.62
    istoitu
    -0.60
    EndContext
    -0.60
    POSITIVE LOGITS
     returns
    0.82
     return
    0.80
     Return
    0.74
    return
    0.70
     IRR
    0.69
     Returns
    0.66
    Return
    0.65
    Returns
    0.64
     discounted
    0.61
     free
    0.60
    Activations Density 0.171%

    No Known Activations