© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12076
    Prev
    Next
    INDEX
    Explanations

    technical terms related to statistical estimators and their properties

    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
     Liss
    -0.53
    DidLoad
    -0.53
    atorze
    -0.52
    æg
    -0.50
    featureID
    -0.49
     néer
    -0.49
    ẫ
    -0.49
     porter
    -0.47
     Substitution
    -0.46
     Gerrit
    -0.46
    POSITIVE LOGITS
     asymptotic
    0.75
     intptr
    0.72
    DockStyle
    0.68
     bound
    0.67
     jsPsych
    0.66
    ConstraintMaker
    0.65
    MessageTagHelper
    0.65
    ympto
    0.64
     asymptotically
    0.64
     tightness
    0.63
    Activations Density 2.668%

    No Known Activations