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
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2457
    Prev
    Next
    INDEX
    Explanations

    comments and code annotations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tangentMode
    -0.68
     ProtoMessage
    -0.62
    发表于
    -0.61
     <=",
    -0.60
    adaptiveStyles
    -0.60
     Infórmanos
    -0.59
    出版年
    -0.56
     okuyayım
    -0.56
     wireType
    -0.55
    ItemBackground
    -0.54
    POSITIVE LOGITS
     somehow
    0.36
     önce
    0.35
    aurait
    0.35
     idéale
    0.34
     pride
    0.33
     upraw
    0.32
     he
    0.32
    起
    0.31
    といって
    0.31
     käyt
    0.31
    Activations Density 0.134%

    No Known Activations