© 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. 8883
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax related to function definitions and control flow in programs

    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
    bootstrapcdn
    -0.80
    urlpatterns
    -0.79
    Décès
    -0.65
    URBANA
    -0.62
    PathVariable
    -0.59
    aarrggbb
    -0.59
    aternion
    -0.57
     useRouter
    -0.57
    fromLTRB
    -0.55
    StoryboardSegue
    -0.53
    POSITIVE LOGITS
    enderror
    0.70
    })()
    0.60
     ***!
    0.57
     "..\..\..\
    0.56
     AssemblyProduct
    0.54
     démocr
    0.54
    iddle
    0.53
    sterne
    0.52
    DebuggerNonUser
    0.51
     Sund
    0.51
    Activations Density 0.076%

    No Known Activations