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. 1681
    Prev
    Next
    INDEX
    Explanations

    concepts related to idealism, justice, and societal critiques

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

    Abstract qualities or concepts

    np_acts-logits-general · gemini-2.0-flash

    abstract qualities and states

    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
     esetén
    -0.66
     alemanes
    -0.58
     tiennent
    -0.57
     entrambi
    -0.56
     alguno
    -0.54
     importantly
    -0.53
     अनुसार
    -0.52
    NameInMap
    -0.52
     sufficiente
    -0.52
     algum
    -0.51
    POSITIVE LOGITS
     confines
    1.10
     intricacies
    1.04
     nature
    1.01
     complexities
    0.95
    liest
    0.92
     realities
    0.91
     extent
    0.90
     implications
    0.88
     workings
    0.86
     majority
    0.86
    Activations Density 0.684%

    No Known Activations