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. 5-GEMMASCOPE-RES-16K
    6. 8658
    Prev
    Next
    INDEX
    Explanations

    terms associated with largescale production or collective events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rhubarb
    -0.87
    theless
    -0.81
     anticoag
    -0.77
    녕
    -0.72
     Ronde
    -0.69
     Anja
    -0.68
    präche
    -0.67
     Vivaldi
    -0.67
     subjec
    -0.66
     kiệm
    -0.65
    POSITIVE LOGITS
     mass
    2.33
     Mass
    2.27
    Mass
    2.09
    mass
    2.06
     MASS
    2.06
    MASS
    2.00
     Massen
    1.78
     masses
    1.76
    masses
    1.55
     Masses
    1.54
    Activations Density 0.055%

    No Known Activations