© 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-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11155
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -1.02
    AndEndTag
    -0.82
    Slf
    -0.79
    MemoryWarning
    -0.74
     pinulongan
    -0.72
    mybatisplus
    -0.71
     Мексичка
    -0.69
     BrowserModule
    -0.68
     ſtill
    -0.68
    GINIA
    -0.68
    POSITIVE LOGITS
     equivalent
    0.49
    elif
    0.45
     contributor
    0.41
     Tale
    0.41
     Duan
    0.40
    ねる
    0.40
     fixture
    0.40
     milestone
    0.40
     consequential
    0.40
     variant
    0.40
    Activations Density 4.744%

    No Known Activations