© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105772
    Prev
    Next
    INDEX
    Explanations

    terms related to wafers and waivers in a legal or technical context

    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
    AnchorStyles
    -0.52
     فريبيس
    -0.47
    ensen
    -0.45
    ➌
    -0.45
    Izzy
    -0.43
    flink
    -0.43
    3
    -0.43
    Источник
    -0.43
    johns
    -0.43
    betrieb
    -0.42
    POSITIVE LOGITS
     Wa
    0.80
     Waiver
    0.79
    Wa
    0.76
     waiver
    0.76
     wa
    0.76
     Waite
    0.74
    wa
    0.71
     waive
    0.71
     Wav
    0.69
     WAV
    0.68
    Activations Density 0.016%

    No Known Activations