© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4076
    Prev
    Next
    INDEX
    Explanations

    references to government actions and political events

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

    Political titles, especially "Minister" or "deputy"

    np_acts-logits-general · gemini-2.0-flash

    political titles and roles

    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
    acterium
    -0.53
    Collegamenti
    -0.53
    <<"\
    -0.51
    +#+#
    -0.50
    VIAF
    -0.50
     niên
    -0.49
    ≦)
    -0.48
    WriteBarrier
    -0.48
    SourceChecksum
    -0.47
    voyer
    -0.47
    POSITIVE LOGITS
     Prime
    1.59
    Prime
    1.38
     Minister
    1.33
     prime
    1.17
     Finance
    1.15
     minister
    1.15
    Minister
    1.10
     ministers
    1.10
     Interior
    1.05
     Opposition
    1.04
    Activations Density 0.285%

    No Known Activations