© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104743
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and references to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    RTLI
    -0.45
     يتيمه
    -0.44
     विश्वसनीयता
    -0.43
    SpringBootTest
    -0.42
    AndroidJUnit
    -0.42
    ":[{
    -0.42
    AddTagHelper
    -0.42
    RTCK
    -0.42
     endwhile
    -0.41
     
    -0.41
    POSITIVE LOGITS
     Савезне
    0.50
    dasarkan
    0.46
    transQ
    0.45
     equations
    0.44
    kontrolle
    0.42
    classnames
    0.42
     figurative
    0.41
     uveden
    0.41
    arashtra
    0.41
    IntoConstraints
    0.41
    Activations Density 0.202%

    No Known Activations