© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8009
    Prev
    Next
    INDEX
    Explanations

    non-standard symbols and formatting

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

    Non-English words or characters

    np_acts-logits-general · gemini-2.0-flash

    variable onset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.79
     незавершена
    -0.69
     nahilalakip
    -0.66
     kaarangay
    -0.58
    RRect
    -0.56
    tangentMode
    -0.55
     تضيفلها
    -0.54
    клопе
    -0.54
     CreateTagHelper
    -0.54
    +#+#
    -0.54
    POSITIVE LOGITS
     quidem
    0.45
     Substance
    0.44
     étr
    0.43
     localObject
    0.43
     �
    0.43
    Weakness
    0.42
    cipline
    0.42
    apiKey
    0.42
    startTime
    0.42
    ge
    0.42
    Activations Density 0.334%

    No Known Activations