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. 3-GEMMASCOPE-RES-16K
    6. 8555
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values or measurements related to data or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.50
    Przeczytaj
    -0.47
    styleType
    -0.44
     Nachmittag
    -0.44
    下载附件
    -0.43
     Мексичка
    -0.42
     continuidad
    -0.42
    katy
    -0.42
    Xna
    -0.41
     صوتيه
    -0.40
    POSITIVE LOGITS
    Билгалдахарш
    0.49
    IntoConstraints
    0.44
    Personensuche
    0.43
     ujednoznacz
    0.42
    migrationBuilder
    0.40
    IUrlHelper
    0.39
     Wikimedijinoj
    0.38
    xxi
    0.38
    TagMode
    0.37
     ivelany
    0.37
    Activations Density 0.706%

    No Known Activations