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. 5721
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and comparison

    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
    ⓧ
    -0.66
    SerializedSize
    -0.52
    Region
    -0.51
    omat
    -0.51
     boxes
    -0.51
    region
    -0.50
    urlpatterns
    -0.50
     Cyl
    -0.49
     box
    -0.49
    onews
    -0.49
    POSITIVE LOGITS
    expandindo
    0.63
     Bridge
    0.59
    Bridge
    0.58
     Mo
    0.57
    mo
    0.56
     BRIDGE
    0.56
     bridges
    0.56
     bridge
    0.56
    getMock
    0.56
     Bridges
    0.56
    Activations Density 1.980%

    No Known Activations