© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3402
    Prev
    Next
    INDEX
    Explanations

    references to authority, particularly religious or spiritual authority

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

    following "God", "divine," or religious terms

    np_acts-logits-general · gemini-2.0-flash

    divine authority and redemption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pertise
    -0.68
    \{\\
    -0.65
    eability
    -0.65
     <>",
    -0.64
     hyster
    -0.64
     Normdatei
    -0.63
     informée
    -0.59
    ﹧
    -0.59
     Assemble
    -0.58
     Vodka
    -0.58
    POSITIVE LOGITS
    UserScript
    0.31
     Livingstone
    0.29
     iti
    0.28
     voudrais
    0.27
     eigener
    0.27
     import
    0.26
     Leistungs
    0.26
     biar
    0.26
     modalités
    0.25
    EditorBrowsable
    0.25
    Activations Density 0.054%

    No Known Activations