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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 16356
    Prev
    Next
    INDEX
    Explanations

    instances of structured question prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddHtmlAttribute
    -0.60
    вгения
    -0.53
     Púb
    -0.51
     Colombie
    -0.50
     Barrios
    -0.50
    esl
    -0.49
    ίδι
    -0.48
     Fears
    -0.48
     údaj
    -0.48
     horaire
    -0.47
    POSITIVE LOGITS
     lenker
    0.93
     يتيمه
    0.87
    .*")]
    0.83
    存于互联网档案馆
    0.82
    TintMode
    0.81
    DockStyle
    0.80
    windowFixed
    0.76
    WebVitals
    0.75
    writeFieldEnd
    0.73
     transfieras
    0.70
    Activations Density 0.082%

    No Known Activations