© 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. 4-GEMMASCOPE-RES-16K
    11. 1412
    Prev
    Next
    INDEX
    Explanations

    references to softness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgumentParser
    -0.85
     propOrder
    -0.82
    ủi
    -0.76
    FormTagHelper
    -0.74
     Diz
    -0.73
    ribune
    -0.72
    orghini
    -0.72
     useRouter
    -0.72
    heon
    -0.71
    DataAnnotations
    -0.70
    POSITIVE LOGITS
     soft
    2.95
     Soft
    2.85
    Soft
    2.76
    soft
    2.74
     SOFT
    2.69
    SOFT
    2.40
     softness
    2.17
     softer
    2.04
     softly
    1.80
     мяг
    1.73
    Activations Density 0.049%

    No Known Activations