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. 1376
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structures in equations or algorithms

    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
    StoryboardSegue
    -0.88
    InvalidProtocol
    -0.82
    Personendaten
    -0.79
    ChildScrollView
    -0.77
    :✨
    -0.75
    protetor
    -0.71
    Портали
    -0.71
     Monfieur
    -0.70
     ویکی‌پدی
    -0.69
    ubereitung
    -0.69
    POSITIVE LOGITS
    awtextra
    0.61
    ↵↵
    0.56
    例文帳に追加
    0.51
     للمعارف
    0.50
    lini
    0.49
     qu
    0.47
    agas
    0.45
     《
    0.43
     <<<<<<<<<<<<<<
    0.42
     sol
    0.41
    Activations Density 0.261%

    No Known Activations