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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15955
    Prev
    Next
    INDEX
    Explanations

    mention of social dynamics and the role of individuals and groups in society

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

    "People" followed by a modal verb

    np_acts-logits-general · gemini-2.0-flash

    groups and their 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
     okaz
    -0.47
    min
    -0.46
     coincides
    -0.44
     Midnight
    -0.44
     coincide
    -0.43
    guin
    -0.41
     idi
    -0.41
     đảo
    -0.41
     represents
    -0.41
    ähren
    -0.40
    POSITIVE LOGITS
     everywhere
    0.81
     يتيمه
    0.76
    ScopeManager
    0.72
     across
    0.71
     nowadays
    0.70
    普遍
    0.66
    everywhere
    0.65
     partout
    0.64
     around
    0.63
     heut
    0.63
    Activations Density 0.349%

    No Known Activations