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

    Neuronpedia

    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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7976
    Prev
    Next
    INDEX
    Explanations

    instances of the words "good" or "great" along with related adjectives and descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suitable
    -0.58
    suitable
    -0.55
     a
    -0.53
     to
    -0.52
     saurait
    -0.48
     geeigne
    -0.47
    Suitable
    -0.46
     entidad
    -0.45
     appropriate
    -0.45
     volgt
    -0.44
    POSITIVE LOGITS
    
    0.86
    webElementXpaths
    0.82
    AccessorTable
    0.76
    omiast
    0.74
    findpost
    0.73
    XmlEnum
    0.73
     onCancelled
    0.69
    ])));
    0.68
     EconPapers
    0.68
    */,
    0.68
    Activations Density 0.516%

    No Known Activations