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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5623
    Prev
    Next
    INDEX
    Explanations

    words associated with the expression of frustration or cursing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
     Bettina
    -0.61
    anInt
    -0.58
    bulaire
    -0.56
    blij
    -0.55
     Swartz
    -0.55
     Bie
    -0.55
     roule
    -0.54
    Życiorys
    -0.54
     cue
    -0.54
     betweenstory
    -0.53
    POSITIVE LOGITS
     dam
    2.81
    dam
    2.64
     Dam
    2.55
     damn
    2.48
    Dam
    2.44
     Damn
    2.22
     DAM
    2.19
     dams
    2.18
    damn
    2.16
     DAMN
    2.14
    Activations Density 0.124%

    No Known Activations