© 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. 12-GEMMASCOPE-RES-16K
    6. 4778
    Prev
    Next
    INDEX
    Explanations

    questions about purpose or reason

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }{*}{
    -0.39
     найден
    -0.35
    recep
    -0.35
     チキン
    -0.35
     []:
    -0.35
    EFAULT
    -0.35
     sal
    -0.34
     sed
    -0.34
    公式
    -0.33
    Invo
    -0.33
    POSITIVE LOGITS
     Administrativna
    0.60
     Which
    0.55
    どのような
    0.54
    Which
    0.52
    UnusedPrivate
    0.51
     welke
    0.49
     welchem
    0.49
    How
    0.49
    ไหน
    0.49
     Welche
    0.48
    Activations Density 0.342%

    No Known Activations