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. 6-GEMMASCOPE-RES-16K
    6. 12257
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical studies and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oader
    -0.89
    antMatchers
    -0.88
     chimique
    -0.87
    ValueGeneration
    -0.85
    GetBytes
    -0.83
    InSection
    -0.81
    上角
    -0.81
    yargs
    -0.79
    fromCharCode
    -0.79
     AssemblyCulture
    -0.79
    POSITIVE LOGITS
     Clin
    1.46
     clinical
    1.44
    Clin
    1.36
     Clinical
    1.33
    clin
    1.30
     Klin
    1.27
    clinical
    1.25
     CLIN
    1.23
    Clinical
    1.23
     clin
    1.22
    Activations Density 0.073%

    No Known Activations