© 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. 25-GEMMASCOPE-RES-16K
    6. 12714
    Prev
    Next
    INDEX
    Explanations

    descriptions of food, particularly highlighting flavors and culinary characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WindowConstants
    -0.78
    脚注の使い方
    -0.58
    ftagPool
    -0.57
    Initializable
    -0.51
    usercontent
    -0.48
    johtaja
    -0.48
     rústico
    -0.47
    /*++
    -0.47
     StringTokenizer
    -0.47
    ượt
    -0.46
    POSITIVE LOGITS
     Pad
    0.69
     cur
    0.68
     pad
    0.62
    Pad
    0.61
    rrggbb
    0.57
     stir
    0.57
     wok
    0.57
    odle
    0.56
     noodles
    0.56
     vermic
    0.55
    Activations Density 0.195%

    No Known Activations