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. 19-GEMMASCOPE-RES-16K
    6. 2223
    Prev
    Next
    INDEX
    Explanations

    elements related to CPU processes and command-line instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adpleegd
    -0.49
     Loos
    -0.49
     Squire
    -0.48
    GOTREF
    -0.47
     GAG
    -0.47
    ינ
    -0.47
     voran
    -0.46
    Retrofit
    -0.46
     verk
    -0.46
    תק
    -0.45
    POSITIVE LOGITS
     Thread
    0.82
    pid
    0.78
     pid
    0.74
    Thread
    0.72
     thread
    0.67
     running
    0.63
    autoreleasepool
    0.63
    ProcessEvent
    0.63
     forks
    0.61
    fork
    0.61
    Activations Density 0.581%

    No Known Activations