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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 10358
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially those indicating excitement or emphasis

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

    Punctuation followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )*/
    -0.74
    InputBorder
    -0.72
     Akismet
    -0.71
    tvguidetime
    -0.70
     Deity
    -0.70
    tagHelper
    -0.70
     GIPHY
    -0.70
     Sodom
    -0.70
     Cæsar
    -0.69
    tagHelperRunner
    -0.69
    POSITIVE LOGITS
     It
    1.52
     There
    1.49
     This
    1.46
     They
    1.41
     These
    1.40
     The
    1.33
     We
    1.32
     If
    1.31
     However
    1.27
     Some
    1.23
    Activations Density 0.515%

    No Known Activations