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-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5910
    Prev
    Next
    INDEX
    Explanations

    references to the term "TI" or its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    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
    -0.60
    WriteLiteral
    -0.54
    Tikang
    -0.49
    interopRequire
    -0.46
    migrationBuilder
    -0.45
    Kilder
    -0.44
    ContentAsync
    -0.43
    ⓧ
    -0.41
     okuyayım
    -0.39
     متعلقه
    -0.38
    POSITIVE LOGITS
    TacToe
    0.48
    tuesday
    0.47
    misu
    0.47
    Diwedd
    0.45
     '\\;'
    0.45
     TUESDAY
    0.39
     Dioxide
    0.39
     Tuesdays
    0.39
     remet
    0.39
    sias
    0.38
    Activations Density 0.227%

    No Known Activations