© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 39453
    Prev
    Next
    INDEX
    Explanations

    references to recipients in various contexts

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

    recipient of communication or data

    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
     ​​
    -0.53
     Law
    -0.52
     law
    -0.50
     Gauss
    -0.47
     Gas
    -0.47
     Air
    -0.47
     how
    -0.47
     gas
    -0.46
     Fire
    -0.46
    law
    -0.46
    POSITIVE LOGITS
     recipient
    2.06
     Recipient
    1.87
    recipient
    1.84
     recipients
    1.83
    Recipient
    1.81
     Recipients
    1.66
    recipients
    1.47
    Recipients
    1.46
    ipient
    1.16
     RECIP
    1.11
    Activations Density 0.003%

    No Known Activations