© 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. 18-GEMMASCOPE-RES-16K
    6. 9502
    Prev
    Next
    INDEX
    Explanations

    topics related to health benefits and lifestyle improvements

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

    followed by "as well" or "too"

    np_acts-logits-general · gemini-2.0-flash

    also and too

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CompleteListener
    -0.76
    Източници
    -0.76
    Filmografia
    -0.75
    ícil
    -0.66
     WaitForSeconds
    -0.65
     StatefulWidget
    -0.64
    errHandler
    -0.64
    Бележки
    -0.64
    localctx
    -0.60
    AntiForgeryToken
    -0.59
    POSITIVE LOGITS
     also
    3.37
    also
    2.88
     também
    2.67
    Also
    2.62
     también
    2.57
     тоже
    2.52
     också
    2.47
     Also
    2.46
     également
    2.38
     też
    2.33
    Activations Density 3.129%

    No Known Activations