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. 2-GEMMASCOPE-RES-16K
    6. 6711
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their diagnostics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    -0.76
    rungsseite
    -0.76
     BrowserModule
    -0.72
    tvguidetime
    -0.69
    Rüyada
    -0.67
    InSection
    -0.64
    ftagPool
    -0.63
    erals
    -0.61
     Wikimédia
    -0.61
     ExecuteAsync
    -0.61
    POSITIVE LOGITS
    ur
    1.33
    UR
    1.25
    uri
    0.90
    ure
    0.85
     ur
    0.84
     UR
    0.82
    urs
    0.81
    Pur
    0.79
     pur
    0.79
    pur
    0.75
    Activations Density 1.945%

    No Known Activations