© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 1708
    Prev
    Next
    INDEX
    Explanations

    key terms related to specific events and monetary aspects in narratives

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    yntaxException
    -0.74
     Italijani
    -0.63
     Spisak
    -0.63
     gynhyrchwyd
    -0.62
     Finlande
    -0.60
    rrggbb
    -0.58
    ativement
    -0.56
     Shakspeare
    -0.55
     vectorielle
    -0.54
    mtrl
    -0.54
    POSITIVE LOGITS
    ChildScrollView
    0.55
    localctx
    0.50
     Wicidata
    0.50
    OnInit
    0.47
    ंदीखरीदारी
    0.47
     OnInit
    0.47
    FormGroup
    0.46
    IUrlHelper
    0.46
     MatDialog
    0.46
    Orm
    0.46
    Activations Density 0.176%

    No Known Activations