© 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. 16-GEMMASCOPE-RES-16K
    11. 4791
    Prev
    Next
    INDEX
    Explanations

    logical triggers that indicate sequential actions or processes

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

    Followed by "you," "the," "these," or "a."

    np_acts-logits-general · gemini-2.0-flash

    completion of a condition

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     CreateTagHelper
    -0.72
     pinulongan
    -0.68
     autrement
    -0.55
    SuspendLayout
    -0.52
    HasColumnName
    -0.50
    adpleegd
    -0.50
     justru
    -0.49
     ведь
    -0.49
     marcher
    -0.48
     malah
    -0.48
    POSITIVE LOGITS
     xong
    0.74
     successfully
    0.62
     sufficiently
    0.60
    IsMutable
    0.59
     satisfactorily
    0.58
     stabili
    0.58
     satisfactory
    0.58
    successfully
    0.57
     stabilize
    0.57
     selesai
    0.56
    Activations Density 0.274%

    No Known Activations