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. 15-GEMMASCOPE-RES-16K
    6. 1704
    Prev
    Next
    INDEX
    Explanations

    numerical data and parameters related to performance or measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -1.07
     lenker
    -1.02
     فريبيس
    -0.96
     nahilalakip
    -0.95
     незавершена
    -0.93
     autorytatywna
    -0.92
     חיצוניים
    -0.92
    GEBURTS
    -0.90
     للمعارف
    -0.89
     дописавши
    -0.89
    POSITIVE LOGITS
    ed
    0.51
    ED
    0.43
    чек
    0.42
    my
    0.39
     viti
    0.38
    xx
    0.38
    son
    0.37
    *********/
    0.37
     Мне
    0.36
    **********/
    0.36
    Activations Density 1.232%

    No Known Activations