© 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. 7447
    Prev
    Next
    INDEX
    Explanations

    references to various roles or titles within sports and education sectors

    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
    JNIEnv
    -0.44
    principalTable
    -0.43
    Amend
    -0.43
     useContext
    -0.41
    WithMany
    -0.40
    出版年
    -0.40
     Amendments
    -0.40
    żyw
    -0.40
     Coronel
    -0.40
    BASEPATH
    -0.39
    POSITIVE LOGITS
     meteoro
    0.44
     LayoutInflater
    0.42
     assistant
    0.42
     ✭✭
    0.41
     ballon
    0.40
    ########.
    0.39
    picasso
    0.39
     chief
    0.38
    是一位
    0.38
     独
    0.38
    Activations Density 0.274%

    No Known Activations