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. 20-GEMMASCOPE-RES-16K
    6. 13716
    Prev
    Next
    INDEX
    Explanations

    relationships between changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.57
     HttpNotFound
    -0.54
     ogóle
    -0.53
     mapStateToProps
    -0.51
    XmlAccessType
    -0.50
     EClass
    -0.48
    toBeTruthy
    -0.47
    PreferredItem
    -0.46
     ThemeData
    -0.44
    reszcie
    -0.44
    POSITIVE LOGITS
     progressively
    1.35
    随着
    1.34
     gradually
    1.32
     Gradually
    1.30
    隨著
    1.30
     conforme
    1.09
     dần
    1.08
    Gradu
    1.03
     progressivement
    0.98
     progre
    0.96
    Activations Density 0.740%

    No Known Activations