© 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. 34-GEMMASCOPE-RES-16K
    11. 11484
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate immediacy or urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finally
    -0.65
     eventually
    -0.63
     finalmente
    -0.61
    finally
    -0.56
     eventual
    -0.54
    eventually
    -0.53
     Eventually
    -0.51
     Finally
    -0.50
     briefly
    -0.50
    Eventually
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.66
     recognisable
    0.63
     gratification
    0.61
     насељу
    0.61
    httphttps
    0.60
     thereafter
    0.59
     recognizable
    0.58
     noDo
    0.57
     disponibilités
    0.56
    KommentareTeilen
    0.55
    Activations Density 0.130%

    No Known Activations