© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12269
    Prev
    Next
    INDEX
    Explanations

    programming concepts and code-related terminology

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

    appearing before "containsKey"

    np_acts-logits-general · gemini-2.0-flash

    database key existence checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desertcart
    -0.57
    TestBed
    -0.44
    extAlignment
    -0.41
     extranjero
    -0.40
     NUKAT
    -0.38
     juzgar
    -0.38
    BarStyle
    -0.38
     buiten
    -0.38
    囗
    -0.37
    Rah
    -0.37
    POSITIVE LOGITS
     redis
    0.65
     Redis
    0.62
    redis
    0.60
    Redis
    0.56
    tanleria
    0.52
    REDIS
    0.49
     prefix
    0.46
    jedis
    0.45
    鍵
    0.44
    ffè
    0.43
    Activations Density 0.217%

    No Known Activations