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. 16-GEMMASCOPE-RES-16K
    6. 12501
    Prev
    Next
    INDEX
    Explanations

    references to creative works and their authors

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

    Follows superlative adjectives

    np_acts-logits-general · gemini-2.0-flash

    qualifying words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $
    -0.66
    <eos>
    -0.64
     "
    -0.63
     '
    -0.61
     
    -0.61
     for
    -0.60
     G
    -0.60
     in
    -0.60
     I
    -0.60
     mit
    -0.59
    POSITIVE LOGITS
     betweenstory
    1.19
     itſelf
    1.07
     ་་
    1.04
     pleaſure
    1.02
    AndEndTag
    1.00
     greateſt
    1.00
     ſeveral
    0.99
     myſelf
    0.98
    исленность
    0.97
     Majefty
    0.95
    Activations Density 0.870%

    No Known Activations