© 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. 24-GEMMASCOPE-RES-16K
    11. 7428
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions or processes related to dynamics and states of being

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

    relating to calmness, softness, and smoothness

    np_acts-logits-general · gemini-2.0-flash

    soft gentle calm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hâte
    -0.71
     compéti
    -0.55
    XmlAccessType
    -0.55
     urgencia
    -0.53
     étan
    -0.52
     yyr
    -0.51
     adev
    -0.51
    RuleContext
    -0.51
    WriteAttribute
    -0.50
    Sper
    -0.50
    POSITIVE LOGITS
     soft
    1.87
     gentle
    1.83
     gentler
    1.62
     softer
    1.61
     gentleness
    1.58
    soft
    1.57
     Soft
    1.54
     softly
    1.53
     softness
    1.50
     SOFT
    1.49
    Activations Density 0.395%

    No Known Activations