© 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. 11-GEMMASCOPE-RES-16K
    11. 4584
    Prev
    Next
    INDEX
    Explanations

    the presence of parentheses in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '/')
    -0.61
     tű
    -0.58
     "/")
    -0.57
     Ca
    -0.54
    ())))
    -0.53
    ())).
    -0.52
    andin
    -0.52
     ‘
    -0.52
    /-/
    -0.51
     Cal
    -0.51
    POSITIVE LOGITS
    +#+#
    0.93
    ConstraintMaker
    0.89
     fubject
    0.80
     demurrer
    0.78
     imageNamed
    0.78
    niająca
    0.77
     avoient
    0.75
     المعيارى
    0.75
    ValueGeneration
    0.75
     étoit
    0.74
    Activations Density 0.097%

    No Known Activations