© 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. 5-GEMMASCOPE-RES-16K
    11. 8982
    Prev
    Next
    INDEX
    Explanations

    occurrences of opening and closing parentheses and certain function signatures or calls in code

    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
     deep
    -0.51
     Go
    -0.50
    isia
    -0.49
    vergne
    -0.47
     or
    -0.43
    clin
    -0.42
     '.')
    -0.41
    atic
    -0.41
    ฬ
    -0.41
     Vor
    -0.41
    POSITIVE LOGITS
     CURIAM
    1.00
    SharedCtor
    0.98
     surla
    0.94
    TestingModule
    0.90
    Przypisy
    0.85
    elemField
    0.82
     createSlice
    0.82
    yntaxException
    0.82
    berdayakan
    0.81
     AssemblyVersion
    0.81
    Activations Density 0.210%

    No Known Activations