© 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. 20-GEMMASCOPE-RES-16K
    6. 12903
    Prev
    Next
    INDEX
    Explanations

    references to established media formats and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.59
    ंदीखरीदारी
    -0.54
     typelib
    -0.50
     ivelany
    -0.48
    lives
    -0.48
     Retriever
    -0.44
    MemoryWarning
    -0.41
     Pref
    -0.41
     PROC
    -0.41
     Preference
    -0.41
    POSITIVE LOGITS
     earliest
    0.69
     early
    0.69
     pioneers
    0.67
    最早
    0.67
     pioneering
    0.64
     oldest
    0.63
     pioneer
    0.61
     vroe
    0.59
     original
    0.58
     frühen
    0.58
    Activations Density 0.311%

    No Known Activations