© 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. 1409
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts related to technological and regulatory aspects in electronic devices and products

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

    structural or physical attributes

    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
    encodeWith
    -0.53
     EconPapers
    -0.50
     utafiti
    -0.49
    انجليز
    -0.46
    VersionUID
    -0.45
    verifyException
    -0.45
     propOrder
    -0.44
    Życiorys
    -0.43
    лтамалар
    -0.43
     Autorisations
    -0.43
    POSITIVE LOGITS
     structural
    0.36
     spatial
    0.36
     visual
    0.35
    Organisateur
    0.35
     physical
    0.35
     stylistic
    0.34
    AndEndTag
    0.34
    roep
    0.33
     compositional
    0.33
     MotionEvent
    0.33
    Activations Density 0.167%

    No Known Activations