© 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. 18-GEMMASCOPE-RES-16K
    11. 10894
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate varying degrees or comparisons

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

    "to [a degree/extent]"

    np_acts-logits-general · gemini-2.0-flash

    extent and degree qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.87
     betweenstory
    -0.77
    InitVars
    -0.76
    UnusedPrivate
    -0.72
     '\\;'
    -0.70
    TabIndex
    -0.67
    NameInMap
    -0.66
     InputDecoration
    -0.64
    ValueGenerated
    -0.62
    WindowConstants
    -0.62
    POSITIVE LOGITS
     extent
    1.70
    extent
    1.44
     degree
    1.34
     Extent
    1.22
    degree
    1.04
     Degree
    1.01
     DEGREE
    0.99
     insofar
    0.98
    Extent
    0.96
    Degree
    0.96
    Activations Density 0.334%

    No Known Activations