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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14017
    Prev
    Next
    INDEX
    Explanations

    expressions and imagery associated with divine or spiritual illumination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StreetMap
    -0.59
    Autoritní
    -0.58
    تقاوى
    -0.56
    RepeatedField
    -0.53
     légales
    -0.52
    adaptiveStyles
    -0.50
     propOrder
    -0.50
     disambiguazione
    -0.49
     calendriers
    -0.48
    lifecycle
    -0.48
    POSITIVE LOGITS
     shine
    1.76
     shining
    1.75
     brightness
    1.60
     bright
    1.60
     brighter
    1.55
     shines
    1.53
     Shine
    1.51
     brightest
    1.49
    shine
    1.47
     radiance
    1.44
    Activations Density 0.151%

    No Known Activations