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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1705
    Prev
    Next
    INDEX
    Explanations

    terms related to inhibition and blocking effects in biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.76
     StringTokenizer
    -0.72
    sizeCache
    -0.70
    ttino
    -0.66
     Bourgoin
    -0.66
    crollView
    -0.65
    fjspx
    -0.64
     tartalomajánló
    -0.64
     فريبيس
    -0.64
     NavController
    -0.64
    POSITIVE LOGITS
     effective
    0.59
     prestazioni
    0.56
    functioning
    0.54
    能
    0.54
     pengh
    0.53
     efficient
    0.53
     справ
    0.52
    works
    0.51
     functioning
    0.51
     قادر
    0.51
    Activations Density 1.077%

    No Known Activations