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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6972
    Prev
    Next
    INDEX
    Explanations

    specific terms related to technical or academic support structures and acknowledgments in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.51
     propOrder
    -0.51
    BagConstraints
    -0.48
     eût
    -0.45
    äsident
    -0.45
     elettron
    -0.45
     архивлан
    -0.43
    oderma
    -0.43
     inkl
    -0.43
    LayoutConstraint
    -0.43
    POSITIVE LOGITS
    ту
    0.71
    __*/
    0.69
    ]){
    0.69
    Демографія
    0.65
    mergeFrom
    0.65
    FileDescriptor
    0.64
    PROMOTED
    0.63
     typelib
    0.63
    iecie
    0.62
    AuthProvider
    0.62
    Activations Density 1.664%

    No Known Activations