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. 12-GEMMASCOPE-RES-16K
    6. 1198
    Prev
    Next
    INDEX
    Explanations

    concepts related to comprehension and the act of understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.76
    番
    -0.61
    leaflet
    -0.61
     urbanas
    -0.59
     Grossman
    -0.59
     Batu
    -0.58
    datagrid
    -0.58
     colpo
    -0.58
    promo
    -0.58
    ejb
    -0.57
    POSITIVE LOGITS
    understand
    1.73
     Understand
    1.71
    Understand
    1.70
     understand
    1.67
     understands
    1.63
     understanding
    1.57
     understood
    1.46
    understood
    1.46
    understanding
    1.44
     understandings
    1.43
    Activations Density 0.081%

    No Known Activations