© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27822
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity or relationships among groups

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

    quantifiers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    libft
    -0.77
    antism
    -0.58
     gutem
    -0.56
    urysty
    -0.54
    üten
    -0.52
    protoimpl
    -0.52
     summers
    -0.51
    itinéraire
    -0.51
     usefulness
    -0.50
     barnet
    -0.50
    POSITIVE LOGITS
     közül
    0.88
     including
    0.73
     those
    0.71
     who
    0.67
     Signalez
    0.65
    纷纷
    0.65
     members
    0.64
    querySelectorAll
    0.63
     other
    0.63
     listed
    0.62
    Activations Density 0.064%

    No Known Activations