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. 23-GEMMASCOPE-RES-16K
    6. 2484
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic and statistical concepts or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.90
     propOrder
    -0.83
    webElementXpaths
    -0.77
    quelize
    -0.71
     iNdEx
    -0.68
    tagHelperRunner
    -0.68
    SizeF
    -0.64
    AnimationsModule
    -0.62
     pinulongan
    -0.62
     صوتيه
    -0.61
    POSITIVE LOGITS
    others
    0.38
     others
    0.31
     pang
    0.28
    Others
    0.27
    TM
    0.27
    ‌آ
    0.27
    ‌
    0.27
     سر
    0.26
     Others
    0.26
    ®
    0.26
    Activations Density 0.443%

    No Known Activations