© 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. 15-GEMMASCOPE-RES-16K
    11. 1910
    Prev
    Next
    INDEX
    Explanations

    references to worship and spiritual authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused41>
    -0.88
    <unused43>
    -0.88
    <unused74>
    -0.88
    <unused79>
    -0.88
    <unused16>
    -0.88
    <unused8>
    -0.88
    <unused23>
    -0.88
    <unused28>
    -0.88
    <unused3>
    -0.88
    <pad>
    -0.88
    POSITIVE LOGITS
     saying
    0.31
     this
    0.30
     here
    0.30
     They
    0.28
     the
    0.27
     los
    0.26
     etkili
    0.26
     says
    0.25
    ere
    0.25
     word
    0.25
    Activations Density 0.181%

    No Known Activations