© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1415
    Prev
    Next
    INDEX
    Explanations

    concepts related to research collaboration and its outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    programmatic governance and stakeholder insights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     AssemblyTitle
    -0.57
    ContentAsync
    -0.47
    ClientSize
    -0.46
    drugs
    -0.44
    Personensuche
    -0.43
    .$.
    -0.42
    ValueStyle
    -0.41
     drugs
    -0.41
     heapq
    -0.40
    getSystemService
    -0.39
    POSITIVE LOGITS
     prioriti
    0.70
     overarching
    0.69
     programmatic
    0.65
     governance
    0.63
     prioritized
    0.62
     prioritizing
    0.60
     foundational
    0.60
     stakeholder
    0.60
     contextual
    0.59
     organizational
    0.59
    Activations Density 0.127%

    No Known Activations