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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 91967
    Prev
    Next
    INDEX
    Explanations

    instances of the word "implement."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    implementing programs and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     geſch
    -0.78
     itſelf
    -0.75
     beſte
    -0.75
     $_(
    -0.73
     plufieurs
    -0.73
    majánló
    -0.73
     ddelwed
    -0.71
     Monfieur
    -0.69
     Conſ
    -0.69
     Majefty
    -0.69
    POSITIVE LOGITS
     implement
    1.46
     Implement
    1.30
    Implement
    1.22
    implement
    1.16
     implements
    1.03
     implementing
    0.90
     IMPLEMENT
    0.87
    implements
    0.87
    Implementing
    0.84
     implementar
    0.81
    Activations Density 0.009%

    No Known Activations