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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 10596
    Prev
    Next
    INDEX
    Explanations

    HTML and programming structures within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.71
     المعيارى
    -0.66
     оригіналу
    -0.65
    twimg
    -0.61
     AssemblyCulture
    -0.60
     kasarigan
    -0.60
    TargetException
    -0.60
    enumii
    -0.59
     ujednoznacz
    -0.59
    AutoresizingMask
    -0.59
    POSITIVE LOGITS
    div
    0.61
     ExecuteAsync
    0.57
    FormTagHelper
    0.56
    imakasih
    0.54
    TableBody
    0.53
    rss
    0.52
    blockquote
    0.51
    PutMapping
    0.50
    existsSync
    0.50
    tbody
    0.49
    Activations Density 0.369%

    No Known Activations