© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 74
    Prev
    Next
    INDEX
    Explanations

    terms related to biological research and animal studies

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

    Scientific study or experiment

    np_acts-logits-general · gemini-2.0-flash

    scientific investigation

    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
     incentiv
    -1.08
     
    -1.07
     impactful
    -1.01
     onboarding
    -1.00
     microbiome
    -0.96
     nuanced
    -0.86
     leveraging
    -0.85
     proactively
    -0.84
     showcased
    -0.82
     Notably
    -0.82
    POSITIVE LOGITS
     daß
    1.10
    faßt
    1.04
     muß
    1.01
     läßt
    0.97
     mußten
    0.84
    luß
    0.84
     mußte
    0.81
     skall
    0.80
     Daß
    0.79
     Moslem
    0.75
    Activations Density 5.142%

    No Known Activations