© 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. 18-GEMMASCOPE-RES-16K
    11. 14198
    Prev
    Next
    INDEX
    Explanations

    multiple instances of brackets and parentheses

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

    LaTeX image/figure environments and properties

    np_acts-logits-general · gemini-2.0-flash

    image width, path, or size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.90
     незавершена
    -0.81
     themſelves
    -0.73
     ProtoMessage
    -0.73
    writeFieldEnd
    -0.72
     EconPapers
    -0.69
     becauſe
    -0.69
     ujednoznacz
    -0.66
     Theſe
    -0.66
    AndEndTag
    -0.66
    POSITIVE LOGITS
     max
    0.61
    max
    0.61
     height
    0.61
     width
    0.59
     maximum
    0.56
     size
    0.55
     crop
    0.53
     tamaño
    0.52
    width
    0.52
    httphttps
    0.52
    Activations Density 0.090%

    No Known Activations