Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1210
    Prev
    Next
    INDEX
    Explanations

    code that processes form uploads and handles uploaded files

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

    File uploading or file extensions

    np_acts-logits-general · gemini-2.0-flash

    uploaded file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vorbehalten
    -0.56
    \"");
    -0.55
    олові
    -0.52
     Buy
    -0.50
    XmlEnum
    -0.49
     buy
    -0.49
     BUY
    -0.49
    Buy
    -0.48
    WebServlet
    -0.48
    Дереккөздер
    -0.48
    POSITIVE LOGITS
     upload
    1.27
     Upload
    1.21
     uploading
    1.18
     uploaded
    1.13
    Upload
    1.12
    upload
    1.10
     uploads
    1.09
     file
    0.95
     files
    0.93
    上传
    0.91
    Activations Density 0.179%

    No Known Activations