© 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. 24-GEMMASCOPE-RES-16K
    6. 2473
    Prev
    Next
    INDEX
    Explanations

    themes related to symbolism and cultural representations, particularly in the context of marriage and relationships

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

    that mean or relate to "symbol"

    np_acts-logits-general · gemini-2.0-flash

    symbolism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nawr
    -0.61
    깥
    -0.58
    انيف
    -0.58
    Personendaten
    -0.50
    ὴ
    -0.50
     hydrochloride
    -0.49
     Periodicals
    -0.49
    makeConstraints
    -0.49
     FileWriter
    -0.48
    EVALUATION
    -0.48
    POSITIVE LOGITS
     symbolism
    1.96
     symbol
    1.94
     symbo
    1.90
     symbolize
    1.88
     symbolizes
    1.86
     simbo
    1.85
     symbolic
    1.80
     symboli
    1.71
     symbols
    1.70
     symbolically
    1.70
    Activations Density 0.286%

    No Known Activations