© 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. 5-GEMMASCOPE-RES-16K
    11. 6937
    Prev
    Next
    INDEX
    Explanations

    programming and mathematical expressions in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    picasso
    -0.53
    MLLoader
    -0.51
    Glück
    -0.51
     básica
    -0.50
     CreateTagHelper
    -0.48
     TextInputType
    -0.48
     bandoulière
    -0.47
    údo
    -0.46
    RegistryLite
    -0.46
     mắn
    -0.44
    POSITIVE LOGITS
     linkovi
    0.78
    AccessorTable
    0.71
    ########.
    0.70
     otomatig
    0.64
     saites
    0.64
    сылкі
    0.63
    aarrggbb
    0.63
    Andra
    0.60
    badlogic
    0.60
     himo
    0.59
    Activations Density 0.226%

    No Known Activations