© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 16772
    Prev
    Next
    INDEX
    Explanations

    different forms of "ism," particularly those related to social and political ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    table
    -0.71
    et
    -0.68
    er
    -0.68
    o
    -0.66
    able
    -0.65
    an
    -0.63
    roides
    -0.63
    e
    -0.63
    tabular
    -0.62
    ed
    -0.62
    POSITIVE LOGITS
    ism
    1.20
     ism
    1.19
    ISM
    1.17
    alism
    1.16
    mism
    1.15
    itism
    1.06
    antism
    1.03
    vism
    1.02
     Judaism
    1.01
    atism
    1.00
    Activations Density 0.027%

    No Known Activations