© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9828
    Prev
    Next
    INDEX
    Explanations

    references to measurements and units, particularly involving "mph" and polymers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.63
    AccessFile
    -0.57
    KommentareTeilen
    -0.57
    hematical
    -0.56
    saraba
    -0.54
     giro
    -0.54
    TextHelper
    -0.54
    ربای
    -0.53
    tagHelperRunner
    -0.52
    queryInterface
    -0.52
    POSITIVE LOGITS
     Regions
    0.76
    hésite
    0.68
    えます
    0.68
    eries
    0.66
    Regions
    0.65
    erie
    0.65
     µ
    0.65
     dB
    0.64
    jména
    0.63
    µ
    0.63
    Activations Density 0.067%

    No Known Activations