© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3855
    Prev
    Next
    INDEX
    Explanations

    referential words pertaining to religious authority and beliefs

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

    religious and theological concepts related to false authority, cult-like beliefs, and deviation from scriptural truth.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.66
    хьтан
    -0.64
     незавершена
    -0.64
    Clik
    -0.59
    createCanvas
    -0.56
    SOUNDBITE
    -0.56
    QMetaType
    -0.56
     NSCoder
    -0.55
    homonymie
    -0.55
    setVerticalGroup
    -0.55
    POSITIVE LOGITS
     false
    0.53
     Sünde
    0.50
     worldly
    0.47
     pride
    0.46
     sin
    0.44
     False
    0.41
     falsche
    0.40
    false
    0.39
     earthly
    0.39
     secular
    0.39
    Activations Density 0.259%

    No Known Activations