© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12841
    Prev
    Next
    INDEX
    Explanations

    terms related to awareness and understanding of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.41
     buah
    -0.37
    JMenu
    -0.36
    gawai
    -0.34
     Pugh
    -0.34
    Predecesor
    -0.34
     Wikiseite
    -0.34
     festivals
    -0.34
    ondissement
    -0.33
     Bíblia
    -0.33
    POSITIVE LOGITS
     understanding
    1.23
     Understanding
    1.05
     awareness
    1.04
    understanding
    1.02
    awareness
    0.94
    Understanding
    0.91
     Awareness
    0.89
    Awareness
    0.79
     appreciation
    0.79
     comprehension
    0.71
    Activations Density 0.100%

    No Known Activations