© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 9234
    Prev
    Next
    INDEX
    Explanations

    mentions of the name Martin, particularly associated with historical figures like Martin Luther King Jr

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

    Following "Martin" (likely Martin Scorsese)

    np_acts-logits-general · gemini-2.0-flash

    Martin Scorsese

    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
     Endlich
    -0.65
     astore
    -0.63
    +#+#
    -0.61
     MessageBoxIcon
    -0.59
    Identyfik
    -0.58
    InputBorder
    -0.57
    tagHelperRunner
    -0.55
    maline
    -0.55
     autorytatywna
    -0.55
    aktery
    -0.54
    POSITIVE LOGITS
     Luther
    0.81
     Scorsese
    0.67
    Luther
    0.63
    eau
    0.62
     Marietta
    0.61
    cemment
    0.55
     jScrollPane
    0.55
    elli
    0.55
    原始内容存档于
    0.55
     lu
    0.54
    Activations Density 0.118%

    No Known Activations