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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11692
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to distinguishing or differentiating between concepts or entities

    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
     ISNI
    -0.71
    shou
    -0.57
    AsUp
    -0.57
     هيا
    -0.54
     diduga
    -0.54
    otheses
    -0.53
    AfterClass
    -0.53
    isnan
    -0.53
    AccessorTable
    -0.53
     dilaporkan
    -0.53
    POSITIVE LOGITS
     distinguish
    2.84
     distinction
    2.67
     distinguishes
    2.53
     differentiate
    2.42
     distinguished
    2.41
     distinguishing
    2.39
     differentiates
    2.27
    distingu
    2.17
     disting
    2.13
     differentiating
    2.09
    Activations Density 0.078%

    No Known Activations