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. 10-GEMMASCOPE-RES-16K
    6. 2744
    Prev
    Next
    INDEX
    Explanations

    references to saving resources or money

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.79
    complexContent
    -0.64
     Dyke
    -0.61
    SequentialGroup
    -0.59
    Же
    -0.59
    attuale
    -0.59
     GetEnumerator
    -0.59
    YourGuide
    -0.59
    aclk
    -0.58
     heck
    -0.58
    POSITIVE LOGITS
     saved
    1.44
     saves
    1.41
     Saved
    1.39
     Saving
    1.38
     SAVE
    1.38
     Save
    1.37
     saving
    1.36
     SAV
    1.34
     Saves
    1.34
    Save
    1.33
    Activations Density 0.059%

    No Known Activations