© 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. 36-GEMMASCOPE-RES-16K
    11. 11616
    Prev
    Next
    INDEX
    Explanations

    phrases related to realization and acknowledgment of truths or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.54
     Италијани
    -0.53
     них
    -0.48
    protoimpl
    -0.47
    postsleuth
    -0.45
    SBATCH
    -0.45
     الرياضيه
    -0.44
    ToTensor
    -0.43
    OCCURRED
    -0.43
    AddTagHelper
    -0.42
    POSITIVE LOGITS
     they
    1.33
     there
    1.28
     we
    1.25
     she
    1.06
     it
    0.96
     he
    0.89
     theres
    0.86
    there
    0.80
     you
    0.76
     theyre
    0.75
    Activations Density 0.620%

    No Known Activations