Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 3151
    Prev
    Next
    INDEX
    Explanations

    terms related to social justice and individual rights

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

    "society" or related concepts

    np_acts-logits-general · gemini-2.0-flash

    modifying society

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.51
     intptr
    -0.48
    MemoryWarning
    -0.47
     TestBed
    -0.46
    IMPORTED
    -0.45
     wireType
    -0.44
    giarism
    -0.43
     HttpHeaders
    -0.43
    kepada
    -0.43
     Greenway
    -0.43
    POSITIVE LOGITS
     society
    2.84
    society
    2.45
    Society
    2.04
     SOCIETY
    2.03
     Society
    2.01
     societies
    1.91
     sociedad
    1.89
     societal
    1.86
     samfun
    1.75
     sociedade
    1.70
    Activations Density 0.394%

    No Known Activations