Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 9019
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Titles and positions of people

    np_acts-logits-general · gemini-2.0-flash

    official roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comerci
    -0.45
    živ
    -0.44
     marketing
    -0.43
     localize
    -0.43
    げた
    -0.43
    hetti
    -0.42
     townships
    -0.42
     owners
    -0.41
     populations
    -0.41
     ritro
    -0.41
    POSITIVE LOGITS
     Secretary
    0.84
     aides
    0.80
     briefing
    0.79
     Presidential
    0.79
     Secretariat
    0.78
    Presidential
    0.77
     presidencial
    0.76
     presidential
    0.76
     Briefing
    0.75
     Cabinet
    0.74
    Activations Density 0.488%

    No Known Activations