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

    Neuronpedia

    APICircuit 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. 4907
    Prev
    Next
    INDEX
    Explanations

    phrases indicating business operations and trends.

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

    business-related terms and discussions.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to typical or normal conditions, especially in business or organizational contexts. It shows high activation for phrases like "business as usual", "status quo", and "normal circumstances", as well as related concepts like "common" or "the rule".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    "normal" or the status quo

    np_acts-logits-general · gemini-2.0-flash

    normal, usual, common

    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
    PerformLayout
    -0.89
     kasarigan
    -0.75
    rrggbb
    -0.68
    DataAnnotations
    -0.65
    بوابة
    -0.62
    featureID
    -0.60
     cherchés
    -0.58
    LookAnd
    -0.57
    GraphicsUnit
    -0.55
     GenerationType
    -0.55
    POSITIVE LOGITS
     normal
    2.51
    normal
    2.14
    Normal
    2.04
     Normal
    2.04
     norm
    2.01
     NORMAL
    1.97
     normality
    1.83
     normale
    1.82
     normales
    1.75
     normalcy
    1.73
    Activations Density 0.258%

    No Known Activations