© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6495
    Prev
    Next
    INDEX
    Explanations

    expressions related to complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderSide
    -0.63
    fromCharCode
    -0.55
    GEBURTS
    -0.55
     Paglinawan
    -0.54
    thenReturn
    -0.51
     lượt
    -0.50
     pinulongan
    -0.50
     חיצוניים
    -0.49
    VideoCapture
    -0.49
    MediaStore
    -0.47
    POSITIVE LOGITS
     complex
    1.22
    complex
    1.05
     Complex
    1.05
     COMPLEX
    1.03
    Complex
    1.02
     complicated
    1.01
    COMPLEX
    0.98
     complexe
    0.96
     complexity
    0.95
     complexities
    0.95
    Activations Density 0.230%

    No Known Activations