© 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. 13023
    Prev
    Next
    INDEX
    Explanations

    information related to minerals, their properties, and uses in health contexts

    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
    OrNil
    -0.54
    provoking
    -0.52
    ोंने
    -0.51
     consequence
    -0.51
    lossene
    -0.49
    acting
    -0.48
    動機
    -0.48
    ContentAsync
    -0.48
    \|_{\
    -0.48
     œuvre
    -0.47
    POSITIVE LOGITS
     commonly
    1.14
     known
    1.10
     Commonly
    0.98
     popular
    0.94
    commonly
    0.93
    known
    0.89
     popularly
    0.86
     widely
    0.85
    popular
    0.85
     usually
    0.82
    Activations Density 0.515%

    No Known Activations