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. 9-GEMMASCOPE-RES-16K
    6. 9345
    Prev
    Next
    INDEX
    Explanations

    references to sculptures and memorials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    مصادر
    -0.69
    stdc
    -0.49
     Pflanze
    -0.45
     tiens
    -0.45
    hver
    -0.45
    jasmine
    -0.45
    ritage
    -0.45
    cherichia
    -0.44
     Système
    -0.44
    documentclass
    -0.44
    POSITIVE LOGITS
     depicting
    0.84
     statues
    0.82
     sculptures
    0.81
     statue
    0.81
     sculpture
    0.80
     Sculpture
    0.77
     depicts
    0.76
    IUrlHelper
    0.75
     cartoons
    0.74
    scul
    0.72
    Activations Density 0.139%

    No Known Activations