© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12063
    Prev
    Next
    INDEX
    Explanations

    references to threading and task management in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.73
     تضيفلها
    -0.69
     SafeMath
    -0.53
    cun
    -0.53
    atguigu
    -0.52
    MessageTagHelper
    -0.51
    icksburg
    -0.49
    tigo
    -0.49
    elemField
    -0.49
    InteropServices
    -0.48
    POSITIVE LOGITS
     doInBackground
    0.85
    TimerTask
    0.77
     AsyncTask
    0.76
    SBATCH
    0.75
    WaitGroup
    0.75
    ruptedException
    0.74
    PostExecute
    0.68
     jobs
    0.67
     FetchType
    0.64
    pthread
    0.63
    Activations Density 0.128%

    No Known Activations