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

    Neuronpedia

    APICircuit 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. 25-GEMMASCOPE-RES-16K
    6. 10475
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "por" 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 @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.67
    出版年
    -0.63
    ValueStyle
    -0.63
     iprot
    -0.59
     للاسماء
    -0.55
    ]")]
    -0.54
     EconPapers
    -0.52
     HasFactory
    -0.52
    }}=$
    -0.51
     Paglinawan
    -0.50
    POSITIVE LOGITS
    tadora
    0.66
     ende
    0.58
    tadores
    0.57
    menor
    0.55
     favor
    0.53
     Перейти
    0.53
    centa
    0.52
    intenant
    0.50
     مشين
    0.50
     reasons
    0.49
    Activations Density 0.082%

    No Known Activations