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. 16-GEMMASCOPE-RES-16K
    6. 12887
    Prev
    Next
    INDEX
    Explanations

    concepts related to flexibility and adaptability in both contexts and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entren
    -0.47
     Глу
    -0.43
     aDecoder
    -0.39
     глу
    -0.39
    깥
    -0.37
     ElementRef
    -0.37
    aben
    -0.36
    Silent
    -0.36
     Verbre
    -0.36
    świ
    -0.35
    POSITIVE LOGITS
     fluctuating
    0.77
     fluctuations
    0.72
     variability
    0.71
     changeable
    0.70
     fluctuation
    0.70
     flexible
    0.66
     fickle
    0.66
     fluctuate
    0.66
     fluctu
    0.63
     adaptable
    0.61
    Activations Density 0.705%

    No Known Activations