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. 21-GEMMASCOPE-RES-16K
    6. 471
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and expressions, particularly related to variables and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \&
    -0.61
     "
    -0.54
    \}
    -0.54
    {}",
    -0.53
     \%,
    -0.52
    \":
    -0.51
     ?>/
    -0.51
     الرياضيه
    -0.50
     --
    -0.50
     men
    -0.49
    POSITIVE LOGITS
     myſelf
    1.21
     itſelf
    1.14
     Houſe
    1.07
     himſelf
    1.04
     Reſ
    1.03
     raiſ
    1.02
     ſeveral
    1.02
     themſelves
    1.01
     ſever
    0.99
     Jefus
    0.99
    Activations Density 0.121%

    No Known Activations