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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 207
    Prev
    Next
    INDEX
    Explanations

    transitional phrases or actions that indicate change or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    льше
    -0.31
     increasingly
    -0.30
    ագրություններ
    -0.29
    czywiście
    -0.29
     diarias
    -0.28
     бывает
    -0.28
     далее
    -0.28
     Grüße
    -0.28
     atún
    -0.28
    請繼續往下閱讀
    -0.27
    POSITIVE LOGITS
    Autoritní
    0.61
    MessageTagHelper
    0.60
    SequentialGroup
    0.60
    HasBeenSet
    0.60
     Arrived
    0.57
     already
    0.56
     ALREADY
    0.56
     Obtained
    0.55
     telah
    0.54
     Already
    0.54
    Activations Density 0.562%

    No Known Activations