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. 9-GEMMASCOPE-RES-16K
    6. 15229
    Prev
    Next
    INDEX
    Explanations

    elements related to programming functions and structure in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.55
    ↵↵
    -0.47
     Friday
    -0.46
     offers
    -0.46
     افت
    -0.42
     rather
    -0.42
    стя
    -0.41
    xtick
    -0.41
    gy
    -0.41
     today
    -0.41
    POSITIVE LOGITS
    BagLayout
    0.86
     تانيه
    0.82
     chré
    0.78
    sizeCache
    0.75
     leaſt
    0.75
    ειτουργ
    0.74
    __":
    0.74
    __':
    0.74
     HasFactory
    0.74
     uLocal
    0.73
    Activations Density 1.399%

    No Known Activations