© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6288
    Prev
    Next
    INDEX
    Explanations

    instances of the word "settle" and its variations, indicating a focus on resolution or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sleep
    -0.50
     argint
    -0.49
    multirow
    -0.48
     renforcé
    -0.47
    jspb
    -0.47
    Intrinsic
    -0.45
     Intrinsic
    -0.45
    sleep
    -0.45
     intrinsic
    -0.44
    Rohy
    -0.43
    POSITIVE LOGITS
     settle
    1.05
     settles
    1.01
     settled
    1.00
     settling
    0.98
    settle
    0.90
    settled
    0.88
    inputs
    0.86
     Settle
    0.85
    settling
    0.83
     settlement
    0.80
    Activations Density 0.047%

    No Known Activations