© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27730
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasAnnotation
    -0.64
     AssemblyVersion
    -0.57
    DrawerToggle
    -0.57
     contribue
    -0.55
    visor
    -0.52
     organiser
    -0.50
    notifyListeners
    -0.49
     favours
    -0.49
    başı
    -0.48
    printStackTrace
    -0.48
    POSITIVE LOGITS
     ujednoznacz
    0.65
    RegressionTest
    0.64
     "[
    0.64
     “[
    0.63
     pursuant
    0.63
    })]
    0.63
    在于
    0.59
     poveznice
    0.58
    })-
    0.58
     Jeden
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.