© 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. 14062
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate taking actions or making changes

    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
    The
    -0.31
    .
    -0.30
    hogy
    -0.30
    ↵↵
    -0.29
    from
    -0.26
     mariage
    -0.25
     yardımcı
    -0.25
     government
    -0.25
    for
    -0.25
     muối
    -0.24
    POSITIVE LOGITS
     كومونز
    1.23
    ſicht
    1.06
    rungsseite
    1.05
     zwiſchen
    1.04
    <unused74>
    1.02
    <unused8>
    1.02
    [@BOS@]
    1.02
    <unused16>
    1.02
    <unused14>
    1.02
    <unused3>
    1.02
    Activations Density 0.379%

    No Known Activations