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. 3-GEMMASCOPE-RES-16K
    6. 12343
    Prev
    Next
    INDEX
    Explanations

    words indicating significance and importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    enterOuterAlt
    -0.69
    IsContent
    -0.68
     يتيمه
    -0.65
     كومونز
    -0.64
     समीक्षाओं
    -0.61
     Paglinawan
    -0.61
     beginnetje
    -0.60
     TableColumn
    -0.59
    下载附件
    -0.58
     kaarangay
    -0.58
    POSITIVE LOGITS
    ^(@)
    0.88
     Efq
    0.80
    spesies
    0.80
     Monfieur
    0.76
     Majefty
    0.74
     myſelf
    0.74
     faſt
    0.69
     raiſ
    0.68
     preſent
    0.66
     ſeveral
    0.65
    Activations Density 1.138%

    No Known Activations