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. 16-GEMMASCOPE-RES-16K
    6. 2972
    Prev
    Next
    INDEX
    Explanations

    commands or options related to file management and usability in a user interface context

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

    preceding a user interface or tool

    np_acts-logits-general · gemini-2.0-flash

    print dialog

    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
    ⓧ
    -0.85
     يتيمه
    -0.84
    Personendaten
    -0.76
    Tikang
    -0.72
     Италијани
    -0.70
    LLocation
    -0.69
     pinulongan
    -0.67
    примеча
    -0.66
    ArgsConstructor
    -0.65
    出版年
    -0.65
    POSITIVE LOGITS
    dialog
    0.56
     Maske
    0.55
    Dialog
    0.54
    popup
    0.53
     dialog
    0.53
    Win
    0.52
     popup
    0.51
    nEnter
    0.50
     Opens
    0.48
     cade
    0.48
    Activations Density 0.216%

    No Known Activations