© 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. 3-GEMMASCOPE-RES-16K
    11. 6771
    Prev
    Next
    INDEX
    Explanations

    structured mathematical expressions or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Belief
    -0.64
    /**
    -0.64
    SerializeField
    -0.62
    Mixtures
    -0.61
     nonUne
    -0.59
     AppModule
    -0.58
    labus
    -0.58
     Gruber
    -0.57
    insics
    -0.56
    cerpt
    -0.56
    POSITIVE LOGITS
    MemoryWarning
    0.81
     المعيارى
    0.78
    󠁢
    0.72
    sidemargin
    0.71
     InputDecoration
    0.70
     /></
    0.69
    AddTagHelper
    0.69
    \}\\
    0.69
    хьтан
    0.68
    </tbody>
    0.68
    Activations Density 0.108%

    No Known Activations