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. 5-GEMMASCOPE-RES-16K
    6. 14290
    Prev
    Next
    INDEX
    Explanations

    the beginning of various paragraphs or sections in the text (denoted by the <bos> token)

    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
    RegressionTest
    -0.94
    IVEREF
    -0.80
     Monfieur
    -0.77
     Theſe
    -0.74
     myſelf
    -0.73
    GEBURTSDATUM
    -0.72
     springfox
    -0.71
     Efq
    -0.71
    brities
    -0.71
     &___
    -0.70
    POSITIVE LOGITS
    \{\\
    0.57
    translation
    0.56
     also
    0.46
     PhpStorm
    0.46
     séjours
    0.45
     jednocześnie
    0.45
     rest
    0.45
    pañol
    0.44
     पू
    0.43
     involved
    0.43
    Activations Density 0.006%

    No Known Activations