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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9538
    Prev
    Next
    INDEX
    Explanations

    references to political and ideological conflicts

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

    ending in "-ism"

    np_acts-logits-general · gemini-2.0-flash

    ideologies and "-isms"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cleros
    -0.65
     physicist
    -0.59
    EDUC
    -0.54
    inerja
    -0.54
     Technolog
    -0.54
    OGRAPH
    -0.53
    حياته
    -0.52
     lingu
    -0.51
     Lingu
    -0.50
     addict
    -0.50
    POSITIVE LOGITS
     Catholicism
    0.82
    alism
    0.81
     journalism
    0.80
     Christianity
    0.78
    antism
    0.74
     feminism
    0.74
     nationalism
    0.74
     Buddhism
    0.73
     capitalism
    0.73
     diplomacy
    0.72
    Activations Density 0.744%

    No Known Activations