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. 17-GEMMASCOPE-RES-16K
    6. 5210
    Prev
    Next
    INDEX
    Explanations

    pronouns, particularly focused on references to subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ization
    -0.46
    ized
    -0.45
    ื่อน
    -0.43
    ist
    -0.43
    OIR
    -0.42
    hip
    -0.41
    kül
    -0.41
     Faz
    -0.40
    koop
    -0.40
    롤
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    0.98
    BufferException
    0.96
     ostavi
    0.93
    Šaltiniai
    0.92
    Demografie
    0.91
     NUKAT
    0.90
    TagMode
    0.88
     الرياضيه
    0.88
    Datuak
    0.88
     تانيه
    0.87
    Activations Density 0.265%

    No Known Activations