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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8472
    Prev
    Next
    INDEX
    Explanations

    words related to social dynamics and group interactions

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

    before conjunctions or prepositions

    np_acts-logits-general · gemini-2.0-flash

    list terminators and list items

    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
     незавершена
    -0.67
    ":
    -0.66
    :
    -0.65
    ':
    -0.63
    ":
    -0.63
     تضيفلها
    -0.62
     '-';
    -0.62
    oa̍t
    -0.60
    ituary
    -0.60
     '.';
    -0.59
    POSITIVE LOGITS
     etc
    1.41
     ועוד
    1.23
     usw
    1.18
    等等
    1.07
    etc
    1.05
     itp
    0.95
    などなど
    0.94
     samt
    0.93
     Etc
    0.91
     stb
    0.91
    Activations Density 0.726%

    No Known Activations