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. 25-GEMMASCOPE-RES-16K
    6. 5998
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific and technical topics, including measurements and quantities related to research or experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.58
    shtml
    -0.55
     Theſe
    -0.53
    Xna
    -0.52
    providedIn
    -0.51
     few
    -0.51
    GeneratedValue
    -0.51
     gärna
    -0.50
     многих
    -0.50
     dirait
    -0.50
    POSITIVE LOGITS
     apiece
    1.34
     total
    1.26
     totalt
    1.15
    total
    1.13
     per
    1.11
     each
    1.09
     simultaneously
    1.06
     totaling
    1.06
     totalling
    1.03
     plus
    1.01
    Activations Density 0.935%

    No Known Activations