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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7293
    Prev
    Next
    INDEX
    Explanations

    references to individuals, particularly those associated with the name "Mal"

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

    Texts starting with "Mar" or "Mal"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Mar or Mal

    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
     Theſe
    -1.73
     itſelf
    -1.72
     myſelf
    -1.64
     Anſ
    -1.58
     faſt
    -1.52
     pleaſure
    -1.51
     purpoſe
    -1.49
     ་་
    -1.46
    BibitemShut
    -1.45
     reaſon
    -1.44
    POSITIVE LOGITS
    S
    1.00
    G
    0.95
    P
    0.92
    R
    0.91
     Ar
    0.91
     Al
    0.91
    Al
    0.90
    O
    0.90
    B
    0.90
    Ar
    0.89
    Activations Density 0.647%

    No Known Activations