© 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-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11326
    Prev
    Next
    INDEX
    Explanations

    references and teachings related to Christian doctrine and scripture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.77
     queſta
    -0.73
    MLLoader
    -0.66
     wireType
    -0.65
     utafitiHapana
    -0.64
     الحره
    -0.64
    Datuak
    -0.63
     myſelf
    -0.62
    RTEE
    -0.61
    ReusableCell
    -0.60
    POSITIVE LOGITS
     verse
    0.83
     verses
    0.74
     passagem
    0.59
     passage
    0.57
     Verse
    0.53
    verse
    0.50
     notice
    0.50
    Verse
    0.49
     Verses
    0.48
     pasaje
    0.48
    Activations Density 0.168%

    No Known Activations