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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15002
    Prev
    Next
    INDEX
    Explanations

    elements related to design and specifications of vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    iasis
    -0.53
     Necklace
    -0.46
     oport
    -0.46
     uses
    -0.44
    ỗi
    -0.43
    init
    -0.43
     socks
    -0.43
    SYSTEM
    -0.40
    betrieb
    -0.40
    hila
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.83
    tagHelperRunner
    0.78
     Autorizaciones
    0.75
    Hochspringen
    0.73
     Paglinawan
    0.71
     contours
    0.70
    setVerticalGroup
    0.70
    ElementException
    0.69
    олові
    0.69
    DeleteBehavior
    0.67
    Activations Density 0.452%

    No Known Activations