© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2697
    Prev
    Next
    INDEX
    Explanations

    references to childhood and related experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.74
    SharedDtor
    -0.67
    PhysRev
    -0.62
     Taktlose
    -0.61
    AddTagHelper
    -0.60
     FormsModule
    -0.60
    providedIn
    -0.60
     ILogger
    -0.57
     BrowserModule
    -0.55
     للاسماء
    -0.55
    POSITIVE LOGITS
     peores
    0.40
     lanzamiento
    0.39
     plenamente
    0.39
     configuración
    0.38
     competición
    0.38
     gelten
    0.37
     geldt
    0.36
     mentira
    0.36
     consideran
    0.36
     infancia
    0.35
    Activations Density 0.179%

    No Known Activations