© 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. 18-GEMMASCOPE-RES-16K
    11. 8853
    Prev
    Next
    INDEX
    Explanations

    terms related to liquids and fluid states

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

    "liquid" followed by a scientific word

    np_acts-logits-general · gemini-2.0-flash

    liquid followed by descriptive noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.71
    PMailer
    -0.67
    InSection
    -0.65
    ArgsConstructor
    -0.63
     Мексичка
    -0.62
     tachycardia
    -0.60
    MessageOf
    -0.59
     deafness
    -0.58
     ModelExpression
    -0.58
    omiast
    -0.57
    POSITIVE LOGITS
    QUID
    0.84
    Liquid
    0.73
     Liquid
    0.70
    liquid
    0.67
     LIQUID
    0.63
     liquid
    0.59
    quid
    0.58
    WebApplication
    0.57
    Tears
    0.56
     matter
    0.56
    Activations Density 0.095%

    No Known Activations