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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6052
    Prev
    Next
    INDEX
    Explanations

    terms related to maritime speed and propulsion systems

    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
     propOrder
    -0.70
     snippetHide
    -0.68
    AsUp
    -0.64
    enido
    -0.60
     مشين
    -0.59
     isComment
    -0.57
    Сам
    -0.57
    expandindo
    -0.57
     scholars
    -0.56
     koska
    -0.56
    POSITIVE LOGITS
    AspNetCore
    0.77
    GetMapping
    0.66
    textAppearance
    0.59
    RequestMapping
    0.57
    ties
    0.55
    housie
    0.53
    ouw
    0.51
    rop
    0.51
     tor
    0.50
    Equality
    0.49
    Activations Density 1.935%

    No Known Activations