© 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. 20-GEMMASCOPE-RES-16K
    6. 15793
    Prev
    Next
    INDEX
    Explanations

    references to the React framework and its components

    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
     alternative
    -0.40
    alternative
    -0.40
    depor
    -0.36
     kual
    -0.36
    étal
    -0.34
     Barbar
    -0.33
    hollow
    -0.33
    pogon
    -0.33
    過的
    -0.33
    뀐
    -0.33
    POSITIVE LOGITS
    react
    1.30
     StatelessWidget
    0.98
    IContainer
    0.93
    ScopeManager
    0.82
    SequentialGroup
    0.82
     StatefulWidget
    0.81
     NgModule
    0.81
     initComponents
    0.80
     OnInit
    0.79
    Composable
    0.78
    Activations Density 0.010%

    No Known Activations