© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6247
    Prev
    Next
    INDEX
    Explanations

    structured data definitions and object properties in programming contexts

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

    Code or string literals enclosed in quotes

    np_acts-logits-general · gemini-2.0-flash

    proper nouns and quoted strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.50
    endphp
    -0.49
     Paglinawan
    -0.47
    DebuggerNonUser
    -0.46
    ukone
    -0.46
    RegistryLite
    -0.46
    BagConstraints
    -0.45
    いよいよ
    -0.44
    twimg
    -0.42
     preſent
    -0.41
    POSITIVE LOGITS
     test
    0.72
    test
    0.69
    Test
    0.62
     Test
    0.59
    TEST
    0.54
     тесто
    0.53
     testing
    0.52
    hoeddwyd
    0.52
     TEST
    0.52
     blah
    0.51
    Activations Density 0.593%

    No Known Activations