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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 9104
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements in a code or markup context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.89
    Autoritní
    -0.83
     esternos
    -0.79
    ⎨
    -0.78
    PutMapping
    -0.77
    WithIOException
    -0.77
    bootstrapcdn
    -0.75
    viembre
    -0.73
    `,
    
    -0.73
    которые
    -0.69
    POSITIVE LOGITS
    PYX
    0.63
    на
    0.61
    on
    0.60
     Spr
    0.60
     مرئيه
    0.59
     становника
    0.59
    classifiers
    0.59
    anor
    0.58
    heme
    0.58
    "\
    0.57
    Activations Density 1.224%

    No Known Activations