© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105715
    Prev
    Next
    INDEX
    Explanations

    conditional statements and references to potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused79>
    -0.75
    <unused14>
    -0.75
    <unused52>
    -0.74
    <unused80>
    -0.74
    <unused16>
    -0.74
    <unused3>
    -0.74
    <unused8>
    -0.74
    <unused21>
    -0.74
    [@BOS@]
    -0.74
    <pad>
    -0.74
    POSITIVE LOGITS
    還可以
    0.31
     he
    0.27
    还可以
    0.25
     or
    0.24
     bencana
    0.23
    ถม
    0.22
     disesuaikan
    0.22
     bambú
    0.22
    ัฒนา
    0.22
    Auszeichnungen
    0.21
    Activations Density 0.085%

    No Known Activations