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. 20-GEMMASCOPE-RES-16K
    6. 1577
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial reasoning and investment analysis

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

    Preceding text before the word "alone."

    np_acts-logits-general · gemini-2.0-flash

    let alone

    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
     kaarangay
    -0.67
    IContainer
    -0.67
     >=",
    -0.66
    tagHelperRunner
    -0.63
    Története
    -0.56
    PhysRev
    -0.55
    :✨
    -0.54
     Ouverture
    -0.53
    ganu
    -0.53
    ColumnHeaders
    -0.53
    POSITIVE LOGITS
     alone
    4.12
    alone
    3.27
     Alone
    3.23
     ALONE
    3.09
    Alone
    2.67
     allein
    2.43
     alene
    2.42
     alleine
    2.32
     seul
    1.99
     seule
    1.83
    Activations Density 0.694%

    No Known Activations