© 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 - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 9525
    Prev
    Next
    INDEX
    Explanations

    structured programming language syntax and logical flow constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ‘
    -0.63
    COUVER
    -0.60
    JspWriter
    -0.59
    ScopeManager
    -0.58
    InitVars
    -0.54
     pinulongan
    -0.53
    TypeDef
    -0.53
     resource
    -0.51
    『
    -0.50
     betweenstory
    -0.50
    POSITIVE LOGITS
     chré
    0.53
    StoryboardSegue
    0.51
    NewUrlParser
    0.51
     recueil
    0.51
     Epile
    0.50
     marié
    0.49
     InputDecoration
    0.49
     للاسماء
    0.49
     correctes
    0.48
     esimer
    0.48
    Activations Density 0.044%

    No Known Activations