© 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. 18-GEMMASCOPE-RES-16K
    11. 293
    Prev
    Next
    INDEX
    Explanations

    code segments involving arrays and for loops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Java or C++ code snippets

    np_acts-logits-general · gemini-2.0-flash

    programming loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tocado
    -0.50
    WithIOException
    -0.46
    Scrollbar
    -0.45
     tocó
    -0.45
     Gedächt
    -0.44
    EDEFAULT
    -0.43
     <>",
    -0.43
    SharedCtor
    -0.42
    mox
    -0.42
    happened
    -0.41
    POSITIVE LOGITS
     Repeated
    0.87
    repeat
    0.86
    Repeated
    0.84
     repeated
    0.83
    repeated
    0.83
    Repeat
    0.78
     repeti
    0.76
     repeat
    0.75
     repeatedly
    0.73
     until
    0.72
    Activations Density 0.309%

    No Known Activations