© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7384
    Prev
    Next
    INDEX
    Explanations

    themes related to relationships and their complexities

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

    Questions starting with "why"

    np_acts-logits-general · gemini-2.0-flash

    asking why

    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
     Puoi
    -0.31
    tahui
    -0.29
    (@"%@",
    -0.26
     wygląda
    -0.26
     gehad
    -0.25
     zij
    -0.25
     fortfarande
    -0.25
     desideri
    -0.25
     pozio
    -0.24
     aproximado
    -0.24
    POSITIVE LOGITS
     why
    1.66
    why
    1.40
     Why
    1.38
    Why
    1.36
     Зачем
    1.28
     зачем
    1.27
     pourquoi
    1.24
     warum
    1.23
    WHY
    1.17
     WHY
    1.16
    Activations Density 0.388%

    No Known Activations