© 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. 18-GEMMASCOPE-RES-16K
    11. 312
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'survive' and its variations

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

    the word "survive"

    np_acts-logits-general · gemini-2.0-flash

    survival of the fittest

    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
    ⓧ
    -0.85
    ThroughAttribute
    -0.76
     Wikimedijinoj
    -0.64
    GEBURTSDATUM
    -0.62
     चीज़ों
    -0.61
     Marston
    -0.60
     kasarigan
    -0.59
    DotNetBar
    -0.58
     createState
    -0.56
    zości
    -0.55
    POSITIVE LOGITS
     Survive
    0.80
    survival
    0.78
     fittest
    0.77
    Survi
    0.77
     Survi
    0.77
     survi
    0.75
     Survivors
    0.75
     survive
    0.75
     survives
    0.75
    survi
    0.74
    Activations Density 0.116%

    No Known Activations