© 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. 8329
    Prev
    Next
    INDEX
    Explanations

    references to family dynamics and relationships

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

    Following "so" or similar conjunctions

    np_acts-logits-general · gemini-2.0-flash

    so long as

    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
    MenuList
    -0.36
    SOUNDBITE
    -0.36
     febri
    -0.35
    bosity
    -0.34
     utilisons
    -0.34
    irability
    -0.33
     imper
    -0.33
    DataColumn
    -0.32
     Zucker
    -0.31
    それでは
    -0.31
    POSITIVE LOGITS
    只要
    1.09
     provided
    1.07
     föruts
    1.06
     solange
    1.04
     Provided
    1.04
    provided
    1.03
    Provided
    1.02
     بشر
    0.98
     proviso
    0.90
     PROVIDED
    0.88
    Activations Density 1.053%

    No Known Activations