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. 8808
    Prev
    Next
    INDEX
    Explanations

    phrases related to creative or fantastical elements in storytelling

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

    structural markers of formal, technical or expository prose—function words, punctuation and connective/notation cues that signal complex, multi-clause sentences and technical descriptions.

    oai_token-act-pair · gpt-5Triggered 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
     NSCoder
    -0.88
    WithIOException
    -0.84
    DeleteBehavior
    -0.81
    OGND
    -0.81
    IVEREF
    -0.80
     ་་
    -0.74
    AddTagHelper
    -0.74
    ItemBackground
    -0.73
    aarrggbb
    -0.73
    fromnode
    -0.72
    POSITIVE LOGITS
    re
    0.61
    ,
    0.57
     is
    0.55
     un
    0.55
    ini
    0.54
     in
    0.53
     Fig
    0.52
    ra
    0.51
    &
    0.51
    .
    0.51
    Activations Density 0.102%

    No Known Activations