© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4656
    Prev
    Next
    INDEX
    Explanations

    terms related to quantity or volume, specifically "bulk" and "bunch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    optarg
    -0.82
    siery
    -0.72
    waitKey
    -0.71
    nologue
    -0.71
    cinfo
    -0.70
     AttributeSet
    -0.69
    utnant
    -0.66
    KOH
    -0.66
    verwijspagina
    -0.66
     Hatton
    -0.65
    POSITIVE LOGITS
    bulk
    0.87
    Bulk
    0.82
     Bulk
    0.77
     bulk
    0.75
     vertre
    0.72
     các
    0.64
    intra
    0.61
     departs
    0.61
     departing
    0.61
     departures
    0.59
    Activations Density 0.085%

    No Known Activations