Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14880
    Prev
    Next
    INDEX
    Explanations

    connective words and conjunctions that indicate relationships between ideas or phrases

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

    appearing before "and" or "or"

    np_acts-logits-general · gemini-2.0-flash

    and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raiſ
    -0.55
    IndentedString
    -0.50
     amarillas
    -0.50
     StatefulWidget
    -0.47
     artesanales
    -0.47
     senhora
    -0.46
    出版年
    -0.45
     NSCoder
    -0.45
    quinho
    -0.45
     vocês
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    0.43
     luk
    0.41
     Rings
    0.40
     Ring
    0.39
    tle
    0.39
    észetes
    0.38
     Erl
    0.38
     rings
    0.38
     Pretty
    0.38
     Fair
    0.37
    Activations Density 0.443%

    No Known Activations