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. 9151
    Prev
    Next
    INDEX
    Explanations

    phrases related to dissolution and termination of partnerships or agreements

    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
    +#+#
    -0.90
    جغرافيا
    -0.88
     متعلقه
    -0.85
    WithIOException
    -0.83
     utafitiHapana
    -0.79
    InjectAttribute
    -0.74
    SourceChecksum
    -0.73
     muualla
    -0.72
     chi̍t
    -0.70
    ########.
    -0.70
    POSITIVE LOGITS
     farewell
    0.76
     Farewell
    0.67
    Farewell
    0.63
    final
    0.56
     final
    0.55
     goodbye
    0.52
    Final
    0.50
    FINAL
    0.49
     despedida
    0.48
    WindowEvent
    0.47
    Activations Density 0.308%

    No Known Activations