Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 2941
    Prev
    Next
    INDEX
    Explanations

    terms related to liquids and their states or forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -1.03
     titolata
    -0.86
     fotográfico
    -0.85
     AssemblyCulture
    -0.84
    makeConstraints
    -0.83
     vechi
    -0.82
     trypto
    -0.81
     parallax
    -0.81
    BagConstraints
    -0.81
    insegna
    -0.81
    POSITIVE LOGITS
     Liquid
    1.42
    Liquid
    1.39
     liquid
    1.38
    liquid
    1.33
     LIQUID
    1.29
    QUID
    1.24
    quid
    1.11
     liquids
    1.06
     Liquids
    1.06
     liquide
    1.00
    Activations Density 0.107%

    No Known Activations