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

    references to product descriptions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to product descriptions, including terms indicating condition, packaging, imperfections, or features specific to an item.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ölf
    -0.66
    principalTable
    -0.60
    BoxShadow
    -0.49
    kiwa
    -0.49
     onCancelled
    -0.49
    AndEndTag
    -0.49
     TextAlign
    -0.48
    aarrggbb
    -0.47
    tonode
    -0.47
     deploying
    -0.47
    POSITIVE LOGITS
    webElementXpaths
    0.61
     auk
    0.53
     please
    0.53
     Please
    0.53
     considérons
    0.52
     Transportation
    0.51
     polymorph
    0.50
     Items
    0.50
    ραπε
    0.49
    amaged
    0.49
    Activations Density 0.160%

    No Known Activations