© 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. 22-GEMMASCOPE-RES-16K
    11. 5567
    Prev
    Next
    INDEX
    Explanations

    conjunctions, particularly the word "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.75
    ########.
    -0.71
    GOTREF
    -0.59
    IntoConstraints
    -0.58
     AssemblyCompany
    -0.55
     referenties
    -0.54
    .*")]
    -0.54
     للمعارف
    -0.53
     Rocker
    -0.52
    )))));
    -0.52
    POSITIVE LOGITS
     thus
    0.46
     therefore
    0.43
     hence
    0.41
     consequently
    0.41
     subsequently
    0.40
     dadurch
    0.38
     sağlay
    0.37
    klaim
    0.37
     thereby
    0.36
     verkrij
    0.36
    Activations Density 1.039%

    No Known Activations