© 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. 15-GEMMASCOPE-RES-16K
    11. 992
    Prev
    Next
    INDEX
    Explanations

    instances of the word "receive" and its variations, indicating a focus on receipt and reception of items or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.60
     affari
    -0.57
     purpoſe
    -0.55
    addEdge
    -0.55
    stdbool
    -0.53
     ſte
    -0.53
    FontStyle
    -0.53
     barons
    -0.52
     slums
    -0.52
     island
    -0.52
    POSITIVE LOGITS
     receive
    1.45
    receive
    1.40
     received
    1.39
     Receive
    1.34
    Receive
    1.32
     receives
    1.29
    Receiving
    1.25
     receiving
    1.22
     Receiving
    1.22
    received
    1.21
    Activations Density 0.106%

    No Known Activations