© 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. 1278
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical structures and properties, particularly in the context of vector spaces and their characteristics

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

    vector space category

    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
    UnusedPrivate
    -0.50
    __.__
    -0.47
     IBOutlet
    -0.46
    ♥♥
    -0.44
    XmlSchema
    -0.43
    期刊论文
    -0.43
     Schwe
    -0.43
    WriteTagHelper
    -0.42
    jsonwebtoken
    -0.42
    Schwe
    -0.42
    POSITIVE LOGITS
    principalTable
    0.53
    crollView
    0.49
     księ
    0.47
     caneca
    0.47
     cadeira
    0.46
     prostředí
    0.45
     leeftijd
    0.45
     světa
    0.45
     sociedade
    0.44
    Portály
    0.44
    Activations Density 0.103%

    No Known Activations