© 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. 14787
    Prev
    Next
    INDEX
    Explanations

    keywords related to user interactions with a machine, particularly in a crafting or assembling context

    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
    Pranala
    -0.44
    ✨:
    -0.43
     aya
    -0.41
     Wiktionnaire
    -0.41
    DockStyle
    -0.36
    놨
    -0.36
     %}
    -0.36
    omiast
    -0.35
     birth
    -0.35
    igsaw
    -0.35
    POSITIVE LOGITS
     manual
    0.66
     manually
    0.63
     manuelle
    0.59
    fromnode
    0.59
     Manual
    0.59
     MANUAL
    0.58
    manual
    0.57
    Manual
    0.57
     manualmente
    0.57
     Manually
    0.56
    Activations Density 0.722%

    No Known Activations