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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3973
    Prev
    Next
    INDEX
    Explanations

    the verb "is" in various contexts, indicating the presence of definitions or statements of being

    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
    verwijspagina
    -0.78
    ViewImports
    -0.68
     hivyo
    -0.65
    évaluateur
    -0.65
     esfuer
    -0.62
    forRoot
    -0.62
     themſelves
    -0.61
    protoimpl
    -0.60
    etc
    -0.60
     ་་
    -0.59
    POSITIVE LOGITS
     that
    0.98
     twofold
    0.95
     the
    0.89
    在于
    0.88
     simple
    0.83
     simply
    0.74
     probably
    0.70
     whether
    0.70
     threefold
    0.68
     terletak
    0.67
    Activations Density 0.257%

    No Known Activations