© 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. 20-GEMMASCOPE-RES-16K
    11. 15942
    Prev
    Next
    INDEX
    Explanations

    words related to bodily features or actions

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

    Emerging or protruding from something

    np_acts-logits-general · gemini-2.0-flash

    emerging through or out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.78
    contentLoaded
    -0.64
     nakalista
    -0.62
    Tikang
    -0.60
    toMap
    -0.59
    IUrlHelper
    -0.58
    tableFuture
    -0.55
     ✭✭
    -0.55
    ucket
    -0.54
    ">//
    -0.50
    POSITIVE LOGITS
     through
    1.27
    through
    1.18
     Through
    1.13
    Through
    1.11
     THROUGH
    1.09
     peeking
    1.08
     thru
    1.04
     attraverso
    0.99
    thru
    0.98
    THROUGH
    0.96
    Activations Density 0.323%

    No Known Activations