© 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. 33-GEMMASCOPE-RES-16K
    6. 8111
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer hardware and storage systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bord
    -0.50
    ContextHolder
    -0.48
    BrowserModule
    -0.45
     Oswald
    -0.44
    kec
    -0.43
    amenti
    -0.43
     jad
    -0.43
     beginnetje
    -0.42
     col
    -0.41
     propa
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.57
     rack
    0.48
     Storage
    0.48
    
    0.46
    Storage
    0.46
     arrays
    0.45
     racks
    0.45
    !*\
    0.44
     STORAGE
    0.44
     gostar
    0.43
    Activations Density 0.606%

    No Known Activations