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. 18-GEMMASCOPE-RES-16K
    6. 14668
    Prev
    Next
    INDEX
    Explanations

    references to governmental departments and ministries related to various functions and responsibilities

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

    Follows "Ministry of" or "Minister of"

    np_acts-logits-general · gemini-2.0-flash

    Minister of government departments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respiro
    -0.45
     Caledonia
    -0.41
     flexibles
    -0.41
    vén
    -0.41
     adventurous
    -0.39
     miejsco
    -0.38
    édez
    -0.38
     tree
    -0.37
     langue
    -0.37
     Olms
    -0.36
    POSITIVE LOGITS
     Minister
    1.28
     Ministry
    1.20
    Minister
    1.19
     minister
    1.15
     ministry
    1.13
     ministers
    1.09
    Ministry
    1.09
     Ministers
    1.07
     MINISTER
    1.06
    minist
    1.06
    Activations Density 0.110%

    No Known Activations