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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1494
    Prev
    Next
    INDEX
    Explanations

    phrases about successfully achieving goals or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.54
    Démographie
    -0.52
     setObject
    -0.52
    GINIA
    -0.52
    bors
    -0.51
    viewDidLoad
    -0.51
     QName
    -0.51
     tanggung
    -0.51
    LW
    -0.50
    toJSONString
    -0.50
    POSITIVE LOGITS
     successfully
    1.00
     Somehow
    0.94
     somehow
    0.93
    Somehow
    0.93
     miraculously
    0.88
     survived
    0.87
    successfully
    0.87
     managed
    0.86
     riuscito
    0.86
     Successfully
    0.86
    Activations Density 0.249%

    No Known Activations