© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13899
    Prev
    Next
    INDEX
    Explanations

    moments of personal experience and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    something happened randomly or unexpectedly

    np_acts-logits-general · gemini-2.0-flash

    stumbled upon, came across

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apapun
    -0.81
     любых
    -0.72
    就算是
    -0.69
     любые
    -0.68
    今後も
    -0.67
    χρι
    -0.67
    regardless
    -0.66
    哪怕
    -0.64
    рім
    -0.62
    hichever
    -0.62
    POSITIVE LOGITS
     accidentally
    0.92
     while
    0.92
    偶然
    0.92
     overheard
    0.91
     someone
    0.85
     whilst
    0.83
     randomly
    0.83
     случайно
    0.83
    たまたま
    0.81
     somebody
    0.79
    Activations Density 0.472%

    No Known Activations