© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 51560
    Prev
    Next
    INDEX
    Explanations

    references to wireless communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    wireless communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Anton
    -0.36
    ตำ
    -0.34
     Section
    -0.34
     Beck
    -0.34
    เป
    -0.32
     must
    -0.32
     reckon
    -0.32
     Bech
    -0.32
     Chapter
    -0.32
     Da
    -0.32
    POSITIVE LOGITS
     wireless
    2.14
     Wireless
    2.09
    Wireless
    2.06
    wireless
    1.96
     inalámb
    1.48
     inalámbrica
    1.40
     WIRE
    1.27
    無線
    1.27
    无线
    1.27
     inalámbrico
    1.20
    Activations Density 0.003%

    No Known Activations