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. 14-GEMMASCOPE-RES-16K
    6. 10696
    Prev
    Next
    INDEX
    Explanations

    terms related to examination and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    θρω
    -0.50
     Fonseca
    -0.48
    ままで
    -0.47
    луй
    -0.47
    ImageField
    -0.47
     
    -0.46
    ėjimas
    -0.46
    ئه
    -0.45
    ähän
    -0.44
     strikes
    -0.43
    POSITIVE LOGITS
     inspect
    1.06
     inspecting
    1.04
     examine
    0.99
     Inspect
    0.99
     inspec
    0.98
     inspection
    0.97
     Examine
    0.95
     examining
    0.94
     examin
    0.94
    Examine
    0.91
    Activations Density 0.548%

    No Known Activations