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. 2128
    Prev
    Next
    INDEX
    Explanations

    key phrases related to corporate communications and public statements

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

    Refusal to comment or provide information

    np_acts-logits-general · gemini-2.0-flash

    declined to comment

    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
     estekak
    -0.72
     nahilalakip
    -0.69
     "..\..\..\
    -0.65
     EconPapers
    -0.64
    $_['
    -0.64
     createSlice
    -0.61
     transfieras
    -0.60
     izle
    -0.58
     يتيمه
    -0.57
    はじめに
    -0.57
    POSITIVE LOGITS
     comment
    1.29
     declined
    1.21
    comment
    1.03
    Comment
    0.99
     commenting
    0.98
     Comment
    0.96
     COMMENT
    0.87
     comments
    0.85
     declining
    0.80
     коммента
    0.79
    Activations Density 0.141%

    No Known Activations