© 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. 3-GEMMASCOPE-RES-16K
    11. 16014
    Prev
    Next
    INDEX
    Explanations

    references to liquid substrates or substances, particularly in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -1.09
     defaultstate
    -0.91
     propOrder
    -0.88
     AssemblyCulture
    -0.85
     Strava
    -0.83
     condoms
    -0.80
     anaemia
    -0.79
    +#+
    -0.79
    makeConstraints
    -0.78
     Fertility
    -0.78
    POSITIVE LOGITS
     liquid
    2.99
    Liquid
    2.85
     Liquid
    2.84
    liquid
    2.80
     LIQUID
    2.55
     liquids
    2.06
     Liquids
    1.87
     liquide
    1.85
     liquidated
    1.71
    液体
    1.68
    Activations Density 0.085%

    No Known Activations