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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4202
    Prev
    Next
    INDEX
    Explanations

    references to early detection or early occurrences in various contexts

    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
    principalTable
    -0.61
    IntoConstraints
    -0.53
    bootstrapcdn
    -0.50
     BorderSide
    -0.48
    enumii
    -0.47
     jScrollPane
    -0.46
    /**
    -0.43
     setDescription
    -0.41
    GTCX
    -0.41
    olybden
    -0.41
    POSITIVE LOGITS
     early
    2.05
     Early
    1.88
    Early
    1.87
    early
    1.81
     EARLY
    1.76
    EARLY
    1.58
     earlier
    1.34
    早
    1.29
     frühen
    1.23
    早期
    1.23
    Activations Density 0.126%

    No Known Activations