© 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. 7-GEMMASCOPE-RES-16K
    6. 14316
    Prev
    Next
    INDEX
    Explanations

    patterns of URL structures, particularly in API routes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.73
    bras
    -0.69
    aarrggbb
    -0.68
    Tē
    -0.66
    k
    -0.65
     وتسجيلات
    -0.63
     natt
    -0.62
    awaiter
    -0.61
     dovuto
    -0.60
    ن
    -0.60
    POSITIVE LOGITS
    ("/:
    1.04
    ('/:
    1.03
    +"/"+
    0.93
    PathVariable
    0.92
    ("/",
    0.91
    ('/',
    0.90
    ("/{
    0.86
    /${
    0.85
    ("/")
    0.84
    ("/");
    0.83
    Activations Density 0.088%

    No Known Activations