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. 5-GEMMASCOPE-RES-16K
    6. 9813
    Prev
    Next
    INDEX
    Explanations

    references to chemical synthesis processes and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [:,
    -0.85
     ILogger
    -0.80
     AppComponent
    -0.80
    openhauer
    -0.79
    ektiv
    -0.76
     McPherson
    -0.74
    Lah
    -0.68
    ILogger
    -0.68
     Buffy
    -0.68
     Kars
    -0.68
    POSITIVE LOGITS
     synthesis
    1.80
     synthesize
    1.80
     Synthesis
    1.78
     Synthe
    1.77
     synthe
    1.68
     sinte
    1.68
     synthesized
    1.67
    synthesis
    1.58
    Synthesis
    1.57
     synthèse
    1.55
    Activations Density 0.113%

    No Known Activations