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. 12494
    Prev
    Next
    INDEX
    Explanations

    phrases related to holding back or delaying actions or events

    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
     nahilalakip
    -0.80
     فريبيس
    -0.79
     متعلقه
    -0.68
     betweenstory
    -0.65
    TagMode
    -0.62
    mappedBy
    -0.60
    ագրություններ
    -0.60
    rrggbb
    -0.59
     aastal
    -0.57
     surla
    -0.56
    POSITIVE LOGITS
    Holding
    0.90
     held
    0.89
     holds
    0.88
     holding
    0.88
    holding
    0.88
     Holding
    0.84
     hold
    0.81
    HOLD
    0.81
     HOLD
    0.81
     Holds
    0.81
    Activations Density 0.098%

    No Known Activations