© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 6946
    Prev
    Next
    INDEX
    Explanations

    references to specific applications or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    product or service names and announcements with associated descriptions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     usually
    -0.50
     always
    -0.50
     rarely
    -0.47
     often
    -0.46
     commonly
    -0.45
     habitual
    -0.45
     again
    -0.44
    featureID
    -0.44
     많
    -0.43
     завжди
    -0.43
    POSITIVE LOGITS
     launch
    1.02
     launched
    1.00
     launching
    0.98
    Launching
    0.95
     Launched
    0.91
    launched
    0.91
    launch
    0.89
     Launching
    0.87
    Launched
    0.85
     launches
    0.83
    Activations Density 0.416%

    No Known Activations