© 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 - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15898
    Prev
    Next
    INDEX
    Explanations

    references to Java Swing events and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.78
    AxisAlignment
    -0.73
    WriteBarrier
    -0.72
    routeProvider
    -0.70
    makeConstraints
    -0.69
    UnknownFields
    -0.68
    onedDateTime
    -0.68
    
    -0.68
    PropertyChanging
    -0.65
    UnknownFieldSet
    -0.65
    POSITIVE LOGITS
     otherwise
    0.38
    Invoke
    0.38
     proposed
    0.37
     methods
    0.37
     else
    0.36
     the
    0.35
     useful
    0.35
     Dres
    0.35
     renamed
    0.35
     essentially
    0.34
    Activations Density 0.025%

    No Known Activations