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. 18-GEMMASCOPE-RES-16K
    6. 3121
    Prev
    Next
    INDEX
    Explanations

    terms related to spiritual experiences and awakenings

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

    Sudden realizations or insights

    np_acts-logits-general · gemini-2.0-flash

    Eureka moment or epiphany

    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
    MigrationBuilder
    -0.50
    lungen
    -0.50
    ragamo
    -0.48
    DispatchToProps
    -0.47
     CYTHON
    -0.45
    siapkan
    -0.42
     entret
    -0.42
    ussen
    -0.41
    缩
    -0.40
    vejec
    -0.40
    POSITIVE LOGITS
     epi
    1.39
     realization
    1.33
     revelation
    1.32
     realisation
    1.31
     breakthrough
    1.21
     aha
    1.18
     enlightenment
    1.17
     Eureka
    1.10
    Eureka
    1.10
     revelations
    1.10
    Activations Density 0.275%

    No Known Activations