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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9036
    Prev
    Next
    INDEX
    Explanations

    the presence of specific phrases or markers in programming or procedural texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.83
     Paglinawan
    -0.56
    әрмәләр
    -0.54
    章节错误
    -0.52
    Referanser
    -0.51
     autorytatywna
    -0.51
     estekak
    -0.50
     ***!
    -0.48
    ReusableCell
    -0.48
    amssymb
    -0.47
    POSITIVE LOGITS
    戬
    0.45
    webElementXpaths
    0.42
    AISSEE
    0.41
    依
    0.40
     tamam
    0.40
     içinde
    0.40
    assies
    0.40
    ORO
    0.40
    ="#"><
    0.39
    rasında
    0.39
    Activations Density 1.591%

    No Known Activations