Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5645
    Prev
    Next
    INDEX
    Explanations

    instances of the word "offer" and its variations, indicating a focus on the concept of offering or providing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tại
    -0.42
     Ludwig
    -0.41
    Whew
    -0.39
     Walton
    -0.39
     wall
    -0.39
     walls
    -0.38
    myspace
    -0.38
    		
    -0.37
     criminal
    -0.37
     WALL
    -0.37
    POSITIVE LOGITS
     Offer
    1.47
    Offer
    1.35
     offer
    1.28
     OFFER
    1.26
    offer
    1.25
     Offers
    1.20
     Offered
    1.19
     offered
    1.16
    offers
    1.16
    offered
    1.14
    Activations Density 0.063%

    No Known Activations