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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 58423
    Prev
    Next
    INDEX
    Explanations

    instances of the word "between."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "between" typically used to introduce time periods, date ranges, or numerical ranges.

    oai_token-act-pair · claude-4-5-haikuTriggered by @jake
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Hawkeye
    -0.66
     RSSSF
    -0.64
    erweise
    -0.64
     AppColors
    -0.62
     ioe
    -0.60
     étrangères
    -0.59
     complètes
    -0.59
     Anfield
    -0.59
     vectorielles
    -0.58
     Sandi
    -0.56
    POSITIVE LOGITS
    between
    1.78
     Between
    1.76
    Between
    1.72
     between
    1.72
     BETWEEN
    1.70
    BETWEEN
    1.66
     betwixt
    1.53
     tussen
    1.46
     zwischen
    1.45
     Entre
    1.41
    Activations Density 0.063%

    No Known Activations