© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 3460
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and mandates related to rights and actions

    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
    ViewFeatures
    -0.69
    Geplaatst
    -0.65
    ThroughAttribute
    -0.61
    enosti
    -0.60
    CppMethod
    -0.55
    initComponents
    -0.52
    脚注の使い方
    -0.51
     autorytatywna
    -0.50
    Välislingid
    -0.50
    SharedDtor
    -0.50
    POSITIVE LOGITS
     forcing
    2.09
     forced
    1.84
    forcing
    1.75
     force
    1.65
    forced
    1.64
     urging
    1.61
     compel
    1.61
    Forced
    1.58
     Forced
    1.57
     compels
    1.53
    Activations Density 0.822%

    No Known Activations