© 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. 9-GEMMASCOPE-RES-16K
    6. 351
    Prev
    Next
    INDEX
    Explanations

    references to heaven and hell

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conspic
    -0.69
    vábbi
    -0.66
    WireFormatLite
    -0.63
    kule
    -0.61
     Turismo
    -0.60
    وص
    -0.59
    phosa
    -0.56
     CAG
    -0.55
    Démographie
    -0.54
    ilets
    -0.54
    POSITIVE LOGITS
     heaven
    1.28
    heaven
    1.26
     Heaven
    1.19
    Heaven
    1.17
     HEAVEN
    1.14
     heavens
    1.06
     Heavens
    0.99
    Paradise
    0.98
     cielo
    0.94
     paraíso
    0.92
    Activations Density 0.086%

    No Known Activations