© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14228
    Prev
    Next
    INDEX
    Explanations

    references to political positions and appointments

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

    preceding a government position

    np_acts-logits-general · gemini-2.0-flash

    shadow minister or secretary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Conductor
    -0.64
    Soorten
    -0.59
     conductor
    -0.53
     surla
    -0.53
     跳转至
    -0.52
     conductors
    -0.51
    Hozzáférés
    -0.51
     Conductor
    -0.50
     anode
    -0.50
    lavi
    -0.49
    POSITIVE LOGITS
     minister
    1.43
     Minister
    1.41
    Minister
    1.26
    minister
    1.22
     ministers
    1.21
     ministry
    1.21
     Ministers
    1.15
    minist
    1.11
     ministre
    1.06
     Ministry
    1.05
    Activations Density 0.154%

    No Known Activations